We gratefully acknowledge support from
the Simons Foundation and member institutions.

Machine Learning

Authors and titles for recent submissions

[ total of 931 entries: 1-656 | 657-931 ]
[ showing 656 entries per page: fewer | more | all ]

Fri, 24 May 2024

[1]  arXiv:2405.14861 [pdf, ps, other]
Title: Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
Authors: Gen Li, Yuling Yan
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Statistics Theory (math.ST); Machine Learning (stat.ML)
[2]  arXiv:2405.14860 [pdf, other]
Title: Not All Language Model Features Are Linear
Comments: Code and data at this https URL
Subjects: Machine Learning (cs.LG)
[3]  arXiv:2405.14853 [pdf, other]
Title: Privileged Sensing Scaffolds Reinforcement Learning
Comments: ICLR 2024 Spotlight version
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
[4]  arXiv:2405.14852 [pdf, other]
Title: PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
Comments: Preprint
Subjects: Machine Learning (cs.LG)
[5]  arXiv:2405.14837 [pdf, other]
Title: Analysis of Atom-level pretraining with QM data for Graph Neural Networks Molecular property models
Comments: 6 pages + 10 Supplement Materials
Subjects: Machine Learning (cs.LG); Chemical Physics (physics.chem-ph); Quantum Physics (quant-ph)
[6]  arXiv:2405.14813 [pdf, other]
Title: Scalable Optimization in the Modular Norm
Subjects: Machine Learning (cs.LG)
[7]  arXiv:2405.14791 [pdf, other]
Title: Recurrent Early Exits for Federated Learning with Heterogeneous Clients
Comments: Accepted at the 41st International Conference on Machine Learning (ICML 2024)
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)
[8]  arXiv:2405.14790 [pdf, other]
Title: DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
Comments: ICML2024
Subjects: Machine Learning (cs.LG)
[9]  arXiv:2405.14780 [pdf, other]
Title: Metric Flow Matching for Smooth Interpolations on the Data Manifold
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[10]  arXiv:2405.14769 [pdf, other]
Title: Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
Comments: ICML 2024
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
[11]  arXiv:2405.14762 [pdf, other]
Title: Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations
Subjects: Machine Learning (cs.LG); Chemical Physics (physics.chem-ph); Computational Physics (physics.comp-ph); Quantum Physics (quant-ph)
[12]  arXiv:2405.14759 [pdf, ps, other]
Title: Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
Subjects: Machine Learning (cs.LG)
[13]  arXiv:2405.14755 [pdf, other]
Title: Large language models can be zero-shot anomaly detectors for time series?
Subjects: Machine Learning (cs.LG)
[14]  arXiv:2405.14751 [pdf, other]
Title: AGILE: A Novel Framework of LLM Agents
Subjects: Machine Learning (cs.LG)
[15]  arXiv:2405.14749 [pdf, other]
Title: Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
[16]  arXiv:2405.14748 [pdf, other]
Title: MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[17]  arXiv:2405.14745 [pdf, other]
Title: AnyLoss: Transforming Classification Metrics into Loss Functions
Subjects: Machine Learning (cs.LG)
[18]  arXiv:2405.14743 [pdf, other]
Title: Iterative Causal Segmentation: Filling the Gap between Market Segmentation and Marketing Strategy
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[19]  arXiv:2405.14742 [pdf, other]
Title: HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[20]  arXiv:2405.14725 [pdf, other]
Title: A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[21]  arXiv:2405.14714 [pdf, other]
Title: Defining error accumulation in ML atmospheric simulators
Comments: Submitted to NeurIPS 2024. 27 pages (including appendices)
Subjects: Machine Learning (cs.LG)
[22]  arXiv:2405.14689 [pdf, other]
Title: Cascade of phase transitions in the training of Energy-based models
Comments: 19 pages, 6 figures
Subjects: Machine Learning (cs.LG); Disordered Systems and Neural Networks (cond-mat.dis-nn); Statistical Mechanics (cond-mat.stat-mech)
[23]  arXiv:2405.14681 [pdf, other]
Title: Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[24]  arXiv:2405.14670 [pdf, other]
Title: Overcoming the Challenges of Batch Normalization in Federated Learning
Subjects: Machine Learning (cs.LG)
[25]  arXiv:2405.14669 [pdf, other]
Title: Efficiency for Free: Ideal Data Are Transportable Representations
Comments: Code: this https URL
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[26]  arXiv:2405.14664 [pdf, other]
Title: Fisher Flow Matching for Generative Modeling over Discrete Data
Comments: Preprint, Under Review
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[27]  arXiv:2405.14660 [pdf, other]
Title: Implicit In-context Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[28]  arXiv:2405.14657 [pdf, other]
Title: Heteroscedastic Preferential Bayesian Optimization with Informative Noise Distributions
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[29]  arXiv:2405.14655 [pdf, other]
Title: Multi-turn Reinforcement Learning from Preference Human Feedback
Subjects: Machine Learning (cs.LG)
[30]  arXiv:2405.14650 [pdf, other]
Title: PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis
Subjects: Machine Learning (cs.LG)
[31]  arXiv:2405.14645 [pdf, other]
Title: Lagrangian Neural Networks for Reversible Dissipative Evolution
Subjects: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci)
[32]  arXiv:2405.14632 [pdf, other]
Title: Reinforcement Learning for Fine-tuning Text-to-speech Diffusion Models
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[33]  arXiv:2405.14629 [pdf, other]
Title: Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences
Comments: Source code: this https URL
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[34]  arXiv:2405.14623 [pdf, other]
Title: U-TELL: Unsupervised Task Expert Lifelong Learning
Subjects: Machine Learning (cs.LG)
[35]  arXiv:2405.14622 [pdf, other]
Title: Calibrated Self-Rewarding Vision Language Models
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
[36]  arXiv:2405.14620 [pdf, other]
Title: Closed-form Symbolic Solutions: A New Perspective on Solving Partial Differential Equations
Subjects: Machine Learning (cs.LG)
[37]  arXiv:2405.14616 [pdf, other]
Title: TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[38]  arXiv:2405.14608 [pdf, other]
Title: ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification
Comments: Accepted at KDD 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[39]  arXiv:2405.14602 [pdf, other]
Title: Controllable Continual Test-Time Adaptation
Subjects: Machine Learning (cs.LG)
[40]  arXiv:2405.14597 [pdf, other]
Title: Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[41]  arXiv:2405.14596 [pdf, other]
Title: Linear Mode Connectivity in Differentiable Tree Ensembles
Subjects: Machine Learning (cs.LG)
[42]  arXiv:2405.14578 [pdf, other]
Title: Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
Subjects: Machine Learning (cs.LG)
[43]  arXiv:2405.14567 [pdf, other]
Title: EHRMamba: Towards Generalizable and Scalable Foundation Models for Electronic Health Records
Comments: 17 Pages, 4 Figures
Subjects: Machine Learning (cs.LG)
[44]  arXiv:2405.14558 [pdf, other]
Title: FUSE: Fast Unified Simulation and Estimation for PDEs
Subjects: Machine Learning (cs.LG)
[45]  arXiv:2405.14547 [pdf, other]
Title: Causal Effect Identification in a Sub-Population with Latent Variables
Comments: 19 pages, 5 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
[46]  arXiv:2405.14544 [pdf, other]
Title: Nuclear Norm Regularization for Deep Learning
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[47]  arXiv:2405.14527 [pdf, other]
Title: ArchesWeather: An efficient AI weather forecasting model at 1.5° resolution
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[48]  arXiv:2405.14522 [pdf, other]
Title: Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
[49]  arXiv:2405.14521 [pdf, other]
Title: Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
[50]  arXiv:2405.14519 [pdf, ps, other]
Title: A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detection
Subjects: Machine Learning (cs.LG)
[51]  arXiv:2405.14517 [pdf, other]
Title: Identity Inference from CLIP Models using Only Textual Data
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[52]  arXiv:2405.14496 [pdf, other]
Title: Hybrid Global Causal Discovery with Local Search
Subjects: Machine Learning (cs.LG)
[53]  arXiv:2405.14477 [pdf, other]
Title: LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[54]  arXiv:2405.14473 [pdf, other]
Title: Poisson Variational Autoencoder
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC)
[55]  arXiv:2405.14469 [pdf, ps, other]
Title: Generalization of Hamiltonian algorithms
Authors: Andreas Maurer
Subjects: Machine Learning (cs.LG)
[56]  arXiv:2405.14468 [pdf, other]
Title: Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML)
[57]  arXiv:2405.14457 [pdf, other]
Title: Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[58]  arXiv:2405.14449 [pdf, other]
Title: Adversarial Schrödinger Bridge Matching
Subjects: Machine Learning (cs.LG)
[59]  arXiv:2405.14446 [pdf, other]
Title: Worldwide Federated Training of Language Models
Comments: 19 pages, 8 figures, Under Review
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC)
[60]  arXiv:2405.14440 [pdf, other]
Title: Bayesian Adaptive Calibration and Optimal Design
Comments: Preprint, currently under review
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[61]  arXiv:2405.14438 [pdf, other]
Title: LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks
Comments: under review
Subjects: Machine Learning (cs.LG)
[62]  arXiv:2405.14432 [pdf, other]
Title: Boosting Robustness by Clipping Gradients in Distributed Learning
Subjects: Machine Learning (cs.LG)
[63]  arXiv:2405.14425 [pdf, other]
Title: When predict can also explain: few-shot prediction to select better neural latents
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[64]  arXiv:2405.14422 [pdf, other]
Title: Unraveling overoptimism and publication bias in ML-driven science
Comments: 31 pages, 7 figures, 6 tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
[65]  arXiv:2405.14407 [pdf, other]
Title: Gradient Transformation: Towards Efficient and Model-Agnostic Unlearning for Dynamic Graph Neural Networks
Subjects: Machine Learning (cs.LG)
[66]  arXiv:2405.14402 [pdf, other]
Title: Exact Gauss-Newton Optimization for Training Deep Neural Networks
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[67]  arXiv:2405.14399 [pdf, other]
Title: Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networks
Comments: Leverage Kolmogorov-Arnold Networks (KANs) for cognitive diagnosis, enhancing the model interpretability. The diagnosis performance is also improved
Subjects: Machine Learning (cs.LG); Computers and Society (cs.CY)
[68]  arXiv:2405.14384 [pdf, other]
Title: Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models
Comments: Accepted at IEEE/CVF Computer Vision and Pattern Recognition Conference Workshops (CVPRW) 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[69]  arXiv:2405.14377 [pdf, other]
Title: CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[70]  arXiv:2405.14372 [pdf, ps, other]
Title: Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints
Subjects: Machine Learning (cs.LG)
[71]  arXiv:2405.14369 [pdf, other]
Title: RoPINN: Region Optimized Physics-Informed Neural Networks
Subjects: Machine Learning (cs.LG)
[72]  arXiv:2405.14355 [pdf, other]
Title: Retrieval-Augmented Mining of Temporal Logic Specifications from Data
Subjects: Machine Learning (cs.LG)
[73]  arXiv:2405.14352 [pdf, other]
Title: Explaining Graph Neural Networks via Structure-aware Interaction Index
Comments: 30 pages, ICML'24
Subjects: Machine Learning (cs.LG)
[74]  arXiv:2405.14313 [pdf, other]
Title: Smooth Pseudo-Labeling
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[75]  arXiv:2405.14307 [pdf, other]
Title: AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation
Comments: Accepted by KDD 2024
Journal-ref: KDD 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[76]  arXiv:2405.14303 [pdf, other]
Title: Similarity-Navigated Conformal Prediction for Graph Neural Networks
Subjects: Machine Learning (cs.LG)
[77]  arXiv:2405.14297 [pdf, other]
Title: Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
Comments: 9 pages, 21 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[78]  arXiv:2405.14291 [pdf, other]
Title: Variational Bayes for Federated Continual Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
[79]  arXiv:2405.14286 [pdf, other]
Title: Co-Representation Neural Hypergraph Diffusion for Edge-Dependent Node Classification
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[80]  arXiv:2405.14273 [pdf, other]
Title: A fast algorithm to minimize prediction loss of the optimal solution in inverse optimization problem of MILP
Authors: Akira Kitaoka
Comments: 22 pages; comments are welcome
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
[81]  arXiv:2405.14270 [pdf, other]
Title: Sparse $L^1$-Autoencoders for Scientific Data Compression
Comments: 11 pages, 6 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Numerical Analysis (math.NA)
[82]  arXiv:2405.14267 [pdf, other]
Title: A Gap in Time: The Challenge of Processing Heterogeneous IoT Point Data in Buildings
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[83]  arXiv:2405.14264 [pdf, other]
Title: Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspective
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
[84]  arXiv:2405.14260 [pdf, other]
Title: Graph Sparsification via Mixture of Graphs
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[85]  arXiv:2405.14257 [pdf, other]
Title: Deep Learning Methods for Adjusting Global MFD Speed Estimations to Local Link Configurations
Subjects: Machine Learning (cs.LG)
[86]  arXiv:2405.14256 [pdf, other]
Title: ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
Comments: 15 pages
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[87]  arXiv:2405.14253 [pdf, other]
Title: Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Subjects: Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
[88]  arXiv:2405.14252 [pdf, other]
Title: Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
Subjects: Machine Learning (cs.LG)
[89]  arXiv:2405.14250 [pdf, other]
Title: Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors
Subjects: Machine Learning (cs.LG); Image and Video Processing (eess.IV); Probability (math.PR)
[90]  arXiv:2405.14246 [pdf, other]
Title: GCondenser: Benchmarking Graph Condensation
Comments: GCondenser is open-sourced and available at this https URL
Subjects: Machine Learning (cs.LG)
[91]  arXiv:2405.14239 [pdf, other]
Title: Harmony: A Joint Self-Supervised and Weakly-Supervised Framework for Learning General Purpose Visual Representations
Comments: 20 pages, 2 figures
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[92]  arXiv:2405.14232 [pdf, ps, other]
Title: FloodDamageCast: Building Flood Damage Nowcasting with Machine Learning and Data Augmentation
Comments: 20 pages, 6 figures
Subjects: Machine Learning (cs.LG)
[93]  arXiv:2405.14226 [pdf, other]
Title: Variational Delayed Policy Optimization
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[94]  arXiv:2405.14222 [pdf, other]
Title: RAQ-VAE: Rate-Adaptive Vector-Quantized Variational Autoencoder
Comments: Under review
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
[95]  arXiv:2405.14219 [pdf, other]
Title: Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[96]  arXiv:2405.14214 [pdf, other]
Title: A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points
Comments: Accepted by IJCAI 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[97]  arXiv:2405.14203 [pdf, other]
Title: GLaD: Synergizing Molecular Graphs and Language Descriptors for Enhanced Power Conversion Efficiency Prediction in Organic Photovoltaic Devices
Comments: In progress
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Chemical Physics (physics.chem-ph)
[98]  arXiv:2405.14186 [pdf, ps, other]
Title: Fairness Hub Technical Briefs: Definition and Detection of Distribution Shift
Comments: Learning Engineering Virtual Institute
Subjects: Machine Learning (cs.LG); Computers and Society (cs.CY)
[99]  arXiv:2405.14185 [pdf, other]
Title: A structure-aware framework for learning device placements on computation graphs
Subjects: Machine Learning (cs.LG); Performance (cs.PF)
[100]  arXiv:2405.14183 [pdf, other]
Title: Deterministic Policies for Constrained Reinforcement Learning in Polynomial-Time
Authors: Jeremy McMahan
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS)
[101]  arXiv:2405.14176 [pdf, other]
Title: Certified Robustness against Sparse Adversarial Perturbations via Data Localization
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[102]  arXiv:2405.14153 [pdf, other]
Title: A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data
Subjects: Machine Learning (cs.LG)
[103]  arXiv:2405.14147 [pdf, other]
Title: Minimum number of neurons in fully connected layers of a given neural network (the first approximation)
Authors: Oleg I.Berngardt
Comments: 21 pages, 2 figures, 1 table
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[104]  arXiv:2405.14135 [pdf, other]
Title: Learning Geospatial Region Embedding with Heterogeneous Graph
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[105]  arXiv:2405.14133 [pdf, other]
Title: Automated Loss function Search for Class-imbalanced Node Classification
Comments: ICML 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Symbolic Computation (cs.SC)
[106]  arXiv:2405.14132 [pdf, other]
Title: Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization
Comments: Preprint
Subjects: Machine Learning (cs.LG)
[107]  arXiv:2405.14126 [pdf, other]
Title: The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
Comments: 14 pages, 7 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[108]  arXiv:2405.14124 [pdf, ps, other]
Title: Mixture of Experts Meets Prompt-Based Continual Learning
Comments: 34 pages
Subjects: Machine Learning (cs.LG)
[109]  arXiv:2405.14121 [pdf, other]
Title: One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
Comments: A preliminary version appeared in the Proceedings of the 12th International Conference on Learning Representations (ICLR 2024)
Subjects: Machine Learning (cs.LG)
[110]  arXiv:2405.14114 [pdf, other]
Title: Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
Comments: Accepted for Reinforcement Learning Conference (RLC) 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[111]  arXiv:2405.14111 [pdf, other]
Title: Improving Generalization of Deep Neural Networks by Optimum Shifting
Subjects: Machine Learning (cs.LG)
[112]  arXiv:2405.14108 [pdf, other]
Title: Deep Learning for Protein-Ligand Docking: Are We There Yet?
Comments: 22 pages, 1 table, 22 figures. Under review. Code, data, tutorials, and benchmark results are available at this https URL
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Biomolecules (q-bio.BM); Quantitative Methods (q-bio.QM)
[113]  arXiv:2405.14103 [pdf, other]
Title: Online Self-Preferring Language Models
Comments: 20 pages, 9 figures
Subjects: Machine Learning (cs.LG)
[114]  arXiv:2405.14099 [pdf, other]
Title: Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
Subjects: Machine Learning (cs.LG); Numerical Analysis (math.NA)
[115]  arXiv:2405.14096 [pdf, other]
Title: Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
Subjects: Machine Learning (cs.LG); Numerical Analysis (math.NA)
[116]  arXiv:2405.14094 [pdf, other]
Title: Attending to Topological Spaces: The Cellular Transformer
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Algebraic Topology (math.AT); Machine Learning (stat.ML)
[117]  arXiv:2405.14090 [pdf, other]
Title: Actively Learning Combinatorial Optimization Using a Membership Oracle
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[118]  arXiv:2405.14089 [pdf, other]
Title: Improved Canonicalization for Model Agnostic Equivariance
Comments: Accepted to EquiVision workshop, CVPR 2024. 7 pages, 1 figure
Subjects: Machine Learning (cs.LG)
[119]  arXiv:2405.14088 [pdf, other]
Title: High-dimensional Learning with Noisy Labels
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
[120]  arXiv:2405.14082 [pdf, other]
Title: Exclusively Penalized Q-learning for Offline Reinforcement Learning
Comments: 9 pages technical page followed by references and appendix
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[121]  arXiv:2405.14079 [pdf, other]
Title: Advancing Transportation Mode Share Analysis with Built Environment: Deep Hybrid Models with Urban Road Network
Comments: 29 pages
Subjects: Machine Learning (cs.LG)
[122]  arXiv:2405.14073 [pdf, other]
Title: PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
Subjects: Machine Learning (cs.LG)
[123]  arXiv:2405.14066 [pdf, ps, other]
Title: Online Classification with Predictions
Comments: 24 pages
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Machine Learning (stat.ML)
[124]  arXiv:2405.14060 [pdf, ps, other]
Title: Probabilistic Inference in the Era of Tensor Networks and Differential Programming
Comments: 12 pages, 4 figures
Subjects: Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
[125]  arXiv:2405.14051 [pdf, ps, other]
Title: A Concentration Inequality for Maximum Mean Discrepancy (MMD)-based Statistics and Its Application in Generative Models
Subjects: Machine Learning (cs.LG); Statistics Theory (math.ST)
[126]  arXiv:2405.14049 [pdf, other]
Title: Particle physics DL-simulation with control over generated data properties
Subjects: Machine Learning (cs.LG)
[127]  arXiv:2405.14045 [pdf, other]
Title: Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[128]  arXiv:2405.14033 [pdf, other]
Title: Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization
Comments: 6 pages, 4 figures
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[129]  arXiv:2405.14023 [pdf, other]
Title: WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
Subjects: Machine Learning (cs.LG)
[130]  arXiv:2405.14021 [pdf, other]
Title: A Study of Posterior Stability for Time-Series Latent Diffusion
Comments: Paper under review
Subjects: Machine Learning (cs.LG)
[131]  arXiv:2405.14020 [pdf, other]
Title: Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[132]  arXiv:2405.14016 [pdf, other]
Title: Towards a Unified Framework for Evaluating Explanations
Comments: 6 pages. Submitted to HEXED Workshop @ EDM24
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[133]  arXiv:2405.14008 [pdf, other]
Title: Bayesian Inverse Problems with Conditional Sinkhorn Generative Adversarial Networks in Least Volume Latent Spaces
Subjects: Machine Learning (cs.LG)
[134]  arXiv:2405.14007 [pdf, other]
Title: A Practice in Enrollment Prediction with Markov Chain Models
Authors: Yan Zhao, Amy Otteson
Subjects: Machine Learning (cs.LG)
[135]  arXiv:2405.14002 [pdf, other]
Title: Animal Behavior Analysis Methods Using Deep Learning: A Survey
Subjects: Machine Learning (cs.LG)
[136]  arXiv:2405.13998 [pdf, other]
Title: Bridging Operator Learning and Conditioned Neural Fields: A Unifying Perspective
Comments: 23 pages, 13 figures
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[137]  arXiv:2405.13995 [pdf, other]
Title: Leveraging World Events to Predict E-Commerce Consumer Demand under Anomaly
Comments: In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (WSDM 2022), 9 pages
Subjects: Machine Learning (cs.LG)
[138]  arXiv:2405.13994 [pdf, other]
Title: Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint
Subjects: Machine Learning (cs.LG); Discrete Mathematics (cs.DM); Data Structures and Algorithms (cs.DS)
[139]  arXiv:2405.13987 [pdf, other]
Title: Analysis of Corrected Graph Convolutions
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Discrete Mathematics (cs.DM); Statistics Theory (math.ST); Machine Learning (stat.ML)
[140]  arXiv:2405.13983 [pdf, other]
Title: DirectMultiStep: Direct Route Generation for Multi-Step Retrosynthesis
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[141]  arXiv:2405.13980 [pdf, other]
Title: Rank Reduction Autoencoders -- Enhancing interpolation on nonlinear manifolds
Subjects: Machine Learning (cs.LG)
[142]  arXiv:2405.13978 [pdf, other]
Title: Mitigating Interference in the Knowledge Continuum through Attention-Guided Incremental Learning
Comments: Published at 3rd Conference on Lifelong Learning Agents (CoLLAs 2024)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[143]  arXiv:2405.13977 [pdf, other]
Title: Removing Bias from Maximum Likelihood Estimation with Model Autophagy
Comments: 9 Pages, submission for NeurIPS 2024
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[144]  arXiv:2405.13975 [pdf, other]
Title: There is HOPE to Avoid HiPPOs for Long-memory State Space Models
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[145]  arXiv:2405.13972 [pdf, other]
Title: Infinite-Dimensional Feature Interaction
Subjects: Machine Learning (cs.LG)
[146]  arXiv:2405.13965 [pdf, other]
Title: Unleashing the Power of Unlabeled Data: A Self-supervised Learning Framework for Cyber Attack Detection in Smart Grids
Comments: 9 pages, 5 figures
Subjects: Machine Learning (cs.LG)
[147]  arXiv:2405.13964 [pdf, other]
Title: Design Editing for Offline Model-based Optimization
Subjects: Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE)
[148]  arXiv:2405.13961 [pdf, other]
Title: SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA)
[149]  arXiv:2405.13957 [pdf, other]
Title: Exploring the Relationship Between Feature Attribution Methods and Model Performance
Comments: AAAI2024 Workshop on AI for Education - Bridging Innovation and Responsibility
Subjects: Machine Learning (cs.LG)
[150]  arXiv:2405.13956 [pdf, other]
Title: Attention as an RNN
Subjects: Machine Learning (cs.LG)
[151]  arXiv:2405.13954 [pdf, other]
Title: What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[152]  arXiv:2405.13952 [pdf, other]
Title: Spectral Adapter: Fine-Tuning in Spectral Space
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[153]  arXiv:2405.13947 [pdf, other]
Title: Leader Reward for POMO-Based Neural Combinatorial Optimization
Subjects: Machine Learning (cs.LG)
[154]  arXiv:2405.13938 [pdf, other]
Title: eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Numerical Analysis (math.NA)
[155]  arXiv:2405.13937 [pdf, other]
Title: DyGPrompt: Learning Feature and Time Prompts on Dynamic Graphs
Comments: Under review
Subjects: Machine Learning (cs.LG)
[156]  arXiv:2405.13934 [pdf, other]
Title: Text-Free Multi-domain Graph Pre-training:Toward Graph Foundation Models
Comments: Under review
Subjects: Machine Learning (cs.LG)
[157]  arXiv:2405.13922 [pdf, other]
Title: Towards Certification of Uncertainty Calibration under Adversarial Attacks
Comments: 11 pages main paper, appendix included
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[158]  arXiv:2405.13915 [pdf, other]
Title: HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model
Subjects: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
[159]  arXiv:2405.13910 [pdf, other]
Title: Learning Latent Space Hierarchical EBM Diffusion Models
Authors: Jiali Cui, Tian Han
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
[160]  arXiv:2405.13902 [pdf, other]
Title: LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[161]  arXiv:2405.13900 [pdf, other]
Title: Rehearsal-free Federated Domain-incremental Learning
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[162]  arXiv:2405.13888 [pdf, other]
Title: Marrying Causal Representation Learning with Dynamical Systems for Science
Comments: 21 pages, 8 figures, 6 tables
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[163]  arXiv:2405.13868 [pdf, other]
Title: Automatically Identifying Local and Global Circuits with Linear Computation Graphs
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
[164]  arXiv:2405.13867 [pdf, other]
Title: Scaling-laws for Large Time-series Models
Comments: 8 pages, 3 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[165]  arXiv:2405.13866 [pdf, other]
Title: Koopcon: A new approach towards smarter and less complex learning
Comments: 7 pages, 3 figures
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
[166]  arXiv:2405.13861 [pdf, other]
Title: Transformers Learn Temporal Difference Methods for In-Context Reinforcement Learning
Subjects: Machine Learning (cs.LG)
[167]  arXiv:2405.13848 [pdf, other]
Title: Maximum Manifold Capacity Representations in State Representation Learning
Subjects: Machine Learning (cs.LG)
[168]  arXiv:2405.13817 [pdf, other]
Title: Thermodynamic Natural Gradient Descent
Comments: 17 pages, 7 figures
Subjects: Machine Learning (cs.LG); Emerging Technologies (cs.ET)
[169]  arXiv:2405.13812 [pdf, other]
Title: Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform
Subjects: Machine Learning (cs.LG)
[170]  arXiv:2405.13810 [pdf, other]
Title: Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[171]  arXiv:2405.13806 [pdf, other]
Title: Advancing Graph Convolutional Networks via General Spectral Wavelets
Subjects: Machine Learning (cs.LG)
[172]  arXiv:2405.13796 [pdf, other]
Title: Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[173]  arXiv:2405.13791 [pdf, other]
Title: Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Pose
Comments: 16 pages, 8 figures, including main text, bibliography and supplemental material
Subjects: Machine Learning (cs.LG)
[174]  arXiv:2405.13787 [pdf, other]
Title: Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target
Comments: 22 pages, 11 figures
Subjects: Machine Learning (cs.LG)
[175]  arXiv:2405.13785 [pdf, other]
Title: Efficient Two-Stage Gaussian Process Regression Via Automatic Kernel Search and Subsampling
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Probability (math.PR); Machine Learning (stat.ML)
[176]  arXiv:2405.13765 [pdf, ps, other]
Title: On the stability of second order gradient descent for time varying convex functions
Comments: 13 pages, 0 figures
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[177]  arXiv:2405.13763 [pdf, other]
Title: Banded Square Root Matrix Factorization for Differentially Private Model Training
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[178]  arXiv:2405.13759 [pdf, other]
Title: Enhancing Multiscale Simulations with Constitutive Relations-Aware Deep Operator Networks
Subjects: Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE)
[179]  arXiv:2405.13755 [pdf, ps, other]
Title: Offline RL via Feature-Occupancy Gradient Ascent
Comments: 26 pages
Subjects: Machine Learning (cs.LG)
[180]  arXiv:2405.13753 [pdf, other]
Title: A Dynamic Model of Performative Human-ML Collaboration: Theory and Empirical Evidence
Comments: 9 Pages and appendix
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); General Economics (econ.GN)
[181]  arXiv:2405.13746 [pdf, other]
Title: CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
[182]  arXiv:2405.13738 [pdf, ps, other]
Title: Memory capacity of three-layer neural networks with non-polynomial activations
Authors: Liam Madden
Comments: 8 pages
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[183]  arXiv:2405.13729 [pdf, other]
Title: ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
[184]  arXiv:2405.13726 [pdf, other]
Title: Score-based Generative Models with Adaptive Momentum
Subjects: Machine Learning (cs.LG)
[185]  arXiv:2405.13721 [pdf, other]
Title: Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
Comments: 34 pages
Subjects: Machine Learning (cs.LG)
[186]  arXiv:2405.13718 [pdf, other]
Title: Upper and lower memory capacity bounds of transformers for next-token prediction
Comments: 13 pages, 1 figure
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[187]  arXiv:2405.13712 [pdf, other]
Title: Learning Diffusion Priors from Observations by Expectation Maximization
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[188]  arXiv:2405.13711 [pdf, other]
Title: VAE-Var: Variational-Autoencoder-Enhanced Variational Assimilation
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Dynamical Systems (math.DS); Atmospheric and Oceanic Physics (physics.ao-ph)
[189]  arXiv:2405.13707 [pdf, other]
Title: Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[190]  arXiv:2405.13699 [pdf, other]
Title: Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[191]  arXiv:2405.13698 [pdf, other]
Title: How to set AdamW's weight decay as you scale model and dataset size
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[192]  arXiv:2405.13693 [pdf, ps, other]
Title: Uncovering Algorithmic Discrimination: An Opportunity to Revisit the Comparator
Subjects: Machine Learning (cs.LG)
[193]  arXiv:2405.13692 [pdf, other]
Title: Challenging Gradient Boosted Decision Trees with Tabular Transformers for Fraud Detection at Booking.com
Authors: Sergei Krutikov (1), Bulat Khaertdinov (2), Rodion Kiriukhin (1), Shubham Agrawal (1), Kees Jan De Vries (1) ((1) Booking.com, (2) Maastricht University)
Comments: Submitted to CIKM'24, Applied Research track
Subjects: Machine Learning (cs.LG)
[194]  arXiv:2405.13682 [pdf, other]
Title: Constructive Universal Approximation Theorems for Deep Joint-Equivariant Networks by Schur's Lemma
Subjects: Machine Learning (cs.LG); Representation Theory (math.RT); Machine Learning (stat.ML)
[195]  arXiv:2405.13677 [pdf, ps, other]
Title: Naturally Private Recommendations with Determinantal Point Processes
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[196]  arXiv:2405.13666 [pdf, ps, other]
Title: Generalization Bounds for Dependent Data using Online-to-Batch Conversion
Subjects: Machine Learning (cs.LG)
[197]  arXiv:2405.13646 [pdf, ps, other]
Title: A Transformer variant for multi-step forecasting of water level and hydrometeorological sensitivity analysis based on explainable artificial intelligence technology
Subjects: Machine Learning (cs.LG)
[198]  arXiv:2405.13639 [pdf, other]
Title: On Hardware-efficient Inference in Probabilistic Circuits
Subjects: Machine Learning (cs.LG)
[199]  arXiv:2405.13632 [pdf, other]
Title: Task agnostic continual learning with Pairwise layer architecture
Authors: Santtu Keskinen
Subjects: Machine Learning (cs.LG)
[200]  arXiv:2405.13629 [pdf, other]
Title: Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
Subjects: Machine Learning (cs.LG)
[201]  arXiv:2405.13609 [pdf, other]
Title: Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning
Subjects: Machine Learning (cs.LG); Computational Finance (q-fin.CP); Quantum Physics (quant-ph)
[202]  arXiv:2405.13599 [pdf, other]
Title: LogRCA: Log-based Root Cause Analysis for Distributed Services
Comments: Accepted at Euro-Par 2024 as a fullpaper
Subjects: Machine Learning (cs.LG)
[203]  arXiv:2405.13592 [pdf, other]
Title: Almost sure convergence rates of stochastic gradient methods under gradient domination
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[204]  arXiv:2405.13586 [pdf, other]
Title: Bond Graphs for multi-physics informed Neural Networks for multi-variate time series
Comments: 8 pages, 3 figures, paper under review
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[205]  arXiv:2405.13584 [pdf, other]
Title: Emulating Full Client Participation: A Long-Term Client Selection Strategy for Federated Learning
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
[206]  arXiv:2405.13575 [pdf, other]
Title: PDMLP: Patch-based Decomposed MLP for Long-Term Time Series Forecastin
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[207]  arXiv:2405.13557 [pdf, other]
Title: MotionCraft: Physics-based Zero-Shot Video Generation
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[208]  arXiv:2405.13551 [pdf, other]
Title: Large Language Models are Effective Priors for Causal Graph Discovery
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[209]  arXiv:2405.13536 [pdf, other]
Title: Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[210]  arXiv:2405.13535 [pdf, other]
Title: Generalized Laplace Approximation
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[211]  arXiv:2405.13526 [pdf, other]
Title: Understanding Virtual Nodes: Oversmoothing, Oversquashing, and Node Heterogeneity
Subjects: Machine Learning (cs.LG)
[212]  arXiv:2405.13522 [pdf, other]
Title: Beyond Trend and Periodicity: Guiding Time Series Forecasting with Textual Cues
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[213]  arXiv:2405.13511 [pdf, other]
Title: Latent Space Alignment for Semantic Channel Equalization
Comments: Accepted for publication at 2024 IEEE ICMLCN
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Information Theory (cs.IT)
[214]  arXiv:2405.13474 [pdf, other]
Title: Why do explanations fail? A typology and discussion on failures in XAI
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
[215]  arXiv:2405.13453 [pdf, other]
Title: A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[216]  arXiv:2405.13449 [pdf, other]
Title: Input Guided Multiple Deconstruction Single Reconstruction neural network models for Matrix Factorization
Comments: 50 pages, 25 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[217]  arXiv:2405.13445 [pdf, other]
Title: Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training
Comments: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[218]  arXiv:2405.13427 [pdf, ps, other]
Title: Adaptive Fuzzy C-Means with Graph Embedding
Subjects: Machine Learning (cs.LG)
[219]  arXiv:2405.13407 [pdf, other]
Title: Dynamic Context Adaptation and Information Flow Control in Transformers: Introducing the Evaluator Adjuster Unit and Gated Residual Connections
Comments: 10 pages, 2 figures, 4 experiments
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[220]  arXiv:2405.13396 [pdf, other]
Title: Why In-Context Learning Transformers are Tabular Data Classifiers
Comments: 9 pages main body, 22 pages total. Preprint under review
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[221]  arXiv:2405.13393 [pdf, other]
Title: NFCL: Simply interpretable neural networks for a short-term multivariate forecasting
Comments: 24 pages, 9 figures, preprint
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[222]  arXiv:2405.13392 [pdf, other]
Title: Local convergence of min-max algorithms to differentiable equilibrium on Riemannian manifold
Authors: Sixin Zhang
Comments: under review
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML)
[223]  arXiv:2405.13390 [pdf, ps, other]
Title: Convergence analysis of kernel learning FBSDE filter
Subjects: Machine Learning (cs.LG); Numerical Analysis (math.NA); Mathematical Finance (q-fin.MF)
[224]  arXiv:2405.13383 [pdf, other]
Title: Gradient Projection For Parameter-Efficient Continual Learning
Subjects: Machine Learning (cs.LG)
[225]  arXiv:2405.13381 [pdf, ps, other]
Title: Optimizing Search Advertising Strategies: Integrating Reinforcement Learning with Generalized Second-Price Auctions for Enhanced Ad Ranking and Bidding
Comments: Accepted by 2024 5th International Conference on Electronic communication and Artificial Intelligence (ICECAI 2024)
Subjects: Machine Learning (cs.LG)
[226]  arXiv:2405.13378 [pdf, other]
Title: FedCache 2.0: Exploiting the Potential of Distilled Data in Knowledge Cache-driven Federated Learning
Comments: 20 pages, 8 figures, 10 tables
Subjects: Machine Learning (cs.LG)
[227]  arXiv:2405.13375 [pdf, other]
Title: Adaptive Data Analysis for Growing Data
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[228]  arXiv:2405.13372 [pdf, other]
Title: Ada-HGNN: Adaptive Sampling for Scalable Hypergraph Neural Networks
Subjects: Machine Learning (cs.LG)
[229]  arXiv:2405.13365 [pdf, other]
Title: Clipped Uniform Quantizers for Communication-Efficient Federated Learning
Comments: Work in progress
Subjects: Machine Learning (cs.LG); Multiagent Systems (cs.MA); Signal Processing (eess.SP)
[230]  arXiv:2405.13348 [pdf, other]
Title: On the Challenges of Creating Datasets for Analyzing Commercial Sex Advertisements to Assess Human Trafficking Risk and Organized Activity
Comments: LXAI Workshop at the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Subjects: Machine Learning (cs.LG)
[231]  arXiv:2405.13347 [pdf, other]
Title: Time-Series Forecasting and Sequence Learning Using Memristor-based Reservoir System
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR)
[232]  arXiv:2405.13324 [pdf, other]
Title: Adversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[233]  arXiv:2405.13300 [pdf, other]
Title: FAITH: Frequency-domain Attention In Two Horizons for Time Series Forecasting
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[234]  arXiv:2405.13290 [pdf, other]
Title: Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees
Comments: This paper has been accepted by the 2024 International Conference on Modeling, Natural Language Processing and Machine Learning(CMNM 2024)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[235]  arXiv:2405.13288 [pdf, other]
Title: Remarks on Loss Function of Threshold Method for Ordinal Regression Problem
Subjects: Machine Learning (cs.LG)
[236]  arXiv:2405.13268 [pdf, other]
Title: Stochastic Online Conformal Prediction with Semi-Bandit Feedback
Subjects: Machine Learning (cs.LG)
[237]  arXiv:2405.13264 [pdf, other]
Title: Part-based Quantitative Analysis for Heatmaps
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[238]  arXiv:2405.13254 [pdf, other]
Title: System Safety Monitoring of Learned Components Using Temporal Metric Forecasting
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO); Software Engineering (cs.SE)
[239]  arXiv:2405.13227 [pdf, ps, other]
Title: A rapid approach to urban traffic noise mapping with a generative adversarial network
Comments: submitted to Applied Acoustics as a technical note
Subjects: Machine Learning (cs.LG); Applied Physics (physics.app-ph)
[240]  arXiv:2405.13220 [pdf, other]
Title: Paired Autoencoders for Inverse Problems
Comments: 18 pages, 6 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Numerical Analysis (math.NA)
[241]  arXiv:2405.13217 [pdf, other]
Title: Interactive Simulations of Backdoors in Neural Networks
Comments: 13 pages, 7 figures, 1 Table
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[242]  arXiv:2405.13205 [pdf, other]
Title: Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
Subjects: Machine Learning (cs.LG)
[243]  arXiv:2405.13203 [pdf, other]
Title: Modeling Real-Time Interactive Conversations as Timed Diarized Transcripts
Comments: GT and GA contributed equally
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
[244]  arXiv:2405.13193 [pdf, other]
Title: Efficient Imitation Learning with Conservative World Models
Comments: Oral presentation, L4DC 2024
Subjects: Machine Learning (cs.LG)
[245]  arXiv:2405.13191 [pdf, other]
Title: Pragmatic auditing: a pilot-driven approach for auditing Machine Learning systems
Subjects: Machine Learning (cs.LG)
[246]  arXiv:2405.13190 [pdf, other]
Title: Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[247]  arXiv:2405.13187 [pdf, other]
Title: A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis
Subjects: Machine Learning (cs.LG)
[248]  arXiv:2405.13173 [pdf, other]
Title: Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous Data
Comments: 10 pages, 5 figures, ECNLP 7 @ LREC-COLING 2024
Subjects: Machine Learning (cs.LG)
[249]  arXiv:2405.13155 [pdf, other]
Title: ReALLM: A general framework for LLM compression and fine-tuning
Subjects: Machine Learning (cs.LG)
[250]  arXiv:2405.13136 [pdf, other]
Title: Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs
Subjects: Machine Learning (cs.LG)
[251]  arXiv:2405.13093 [pdf, other]
Title: Graph neural networks informed locally by thermodynamics
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[252]  arXiv:2405.13090 [pdf, other]
Title: FedASTA: Federated adaptive spatial-temporal attention for traffic flow prediction
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
[253]  arXiv:2405.13089 [pdf, other]
Title: SEGAN: semi-supervised learning approach for missing data imputation
Subjects: Machine Learning (cs.LG)
[254]  arXiv:2405.13088 [pdf, other]
Title: Combining Relevance and Magnitude for Resource-Aware DNN Pruning
Subjects: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
[255]  arXiv:2405.13082 [pdf, other]
Title: A Survey of Artificial Intelligence in Gait-Based Neurodegenerative Disease Diagnosis
Comments: 35 pages, 9 figures, 5 tables, citing 272 papers, under review at ACM Computing Survey (CSUR) journal. A up-to-date resource (papers, data, etc.) of this survey (AI4NDD) is provided at this https URL
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[256]  arXiv:2405.13078 [pdf, other]
Title: Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch
Subjects: Machine Learning (cs.LG)
[257]  arXiv:2405.13075 [pdf, other]
Title: Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation
Subjects: Machine Learning (cs.LG)
[258]  arXiv:2405.14868 (cross-list from cs.CV) [pdf, other]
Title: Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
Comments: Project webpage is available at: this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
[259]  arXiv:2405.14863 (cross-list from cs.CL) [pdf, other]
Title: A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns
Comments: CogSci
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[260]  arXiv:2405.14857 (cross-list from cs.CV) [pdf, other]
Title: Semantica: An Adaptable Image-Conditioned Diffusion Model
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[261]  arXiv:2405.14854 (cross-list from cs.CV) [pdf, other]
Title: TerDiT: Ternary Diffusion Models with Transformers
Comments: 18 pages, 13 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[262]  arXiv:2405.14848 (cross-list from stat.ML) [pdf, other]
Title: Local Causal Discovery for Structural Evidence of Direct Discrimination
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[263]  arXiv:2405.14840 (cross-list from stat.ML) [pdf, other]
Title: Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
Comments: 22 pages, including 9 pages of main text and 11 pages of appendix, conference paper at ICML 2024
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[264]  arXiv:2405.14838 (cross-list from cs.CL) [pdf, other]
Title: From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[265]  arXiv:2405.14830 (cross-list from hep-lat) [pdf, other]
Title: Deep learning lattice gauge theories
Subjects: High Energy Physics - Lattice (hep-lat); Disordered Systems and Neural Networks (cond-mat.dis-nn); Strongly Correlated Electrons (cond-mat.str-el); Machine Learning (cs.LG); High Energy Physics - Theory (hep-th)
[266]  arXiv:2405.14822 (cross-list from cs.CV) [pdf, other]
Title: PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
[267]  arXiv:2405.14808 (cross-list from cs.CL) [pdf, other]
Title: Implicit Personalization in Language Models: A Systematic Study
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
[268]  arXiv:2405.14806 (cross-list from physics.data-an) [pdf, other]
Title: Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
Comments: 10+12 pages, 5+2 figures, 2 tables
Subjects: Data Analysis, Statistics and Probability (physics.data-an); Machine Learning (cs.LG); High Energy Physics - Phenomenology (hep-ph); Machine Learning (stat.ML)
[269]  arXiv:2405.14779 (cross-list from cs.CL) [pdf, other]
Title: Smart Bilingual Focused Crawling of Parallel Documents
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[270]  arXiv:2405.14778 (cross-list from stat.ML) [pdf, ps, other]
Title: Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[271]  arXiv:2405.14776 (cross-list from cond-mat.str-el) [pdf, other]
Title: Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations
Comments: 17 pages, 11 figures
Subjects: Strongly Correlated Electrons (cond-mat.str-el); Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
[272]  arXiv:2405.14768 (cross-list from cs.CL) [pdf, other]
Title: WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Comments: Work in progress
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR); Machine Learning (cs.LG)
[273]  arXiv:2405.14767 (cross-list from q-fin.ST) [pdf, other]
Title: FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
Comments: FinRobot Whitepaper V1.0
Subjects: Statistical Finance (q-fin.ST); Computation and Language (cs.CL); Machine Learning (cs.LG); Trading and Market Microstructure (q-fin.TR)
[274]  arXiv:2405.14766 (cross-list from cs.CL) [pdf, other]
Title: Evaluating Large Language Models for Public Health Classification and Extraction Tasks
Comments: 33 pages. Feedback and comments are highly appreciated
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[275]  arXiv:2405.14758 (cross-list from cs.GT) [pdf, ps, other]
Title: Axioms for AI Alignment from Human Feedback
Subjects: Computer Science and Game Theory (cs.GT); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[276]  arXiv:2405.14754 (cross-list from cs.CE) [pdf, other]
Title: Applied Machine Learning to Anomaly Detection in Enterprise Purchase Processes
Subjects: Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
[277]  arXiv:2405.14753 (cross-list from cs.SE) [pdf, other]
Title: A Transformer-Based Approach for Smart Invocation of Automatic Code Completion
Comments: 10 pages, 3 figures; Accepted at FSE AIWARE'24
Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
[278]  arXiv:2405.14750 (cross-list from astro-ph.SR) [pdf, other]
Title: Extreme Solar Flare Prediction Using Residual Networks with HMI Magnetograms and Intensitygrams
Comments: submitted to SPAICE Conference 2024
Subjects: Solar and Stellar Astrophysics (astro-ph.SR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[279]  arXiv:2405.14741 (cross-list from math.OC) [pdf, other]
Title: Bagging Improves Generalization Exponentially
Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG)
[280]  arXiv:2405.14736 (cross-list from cs.CV) [pdf, other]
Title: GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
Comments: this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[281]  arXiv:2405.14734 (cross-list from cs.CL) [pdf, other]
Title: SimPO: Simple Preference Optimization with a Reference-Free Reward
Comments: Code: this https URL
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[282]  arXiv:2405.14730 (cross-list from cs.CV) [pdf, other]
Title: Embedding Compression for Efficient Re-Identification
Authors: Luke McDermott
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[283]  arXiv:2405.14728 (cross-list from cs.AI) [pdf, ps, other]
Title: Intervention and Conditioning in Causal Bayesian Networks
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[284]  arXiv:2405.14719 (cross-list from math.OC) [pdf, other]
Title: Decision-Focused Forecasting: Decision Losses for Multistage Optimisation
Comments: Under review. Preprint
Subjects: Optimization and Control (math.OC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[285]  arXiv:2405.14677 (cross-list from cs.CV) [pdf, other]
Title: RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[286]  arXiv:2405.14630 (cross-list from stat.ML) [pdf, ps, other]
Title: Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
Comments: 47 pages
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[287]  arXiv:2405.14600 (cross-list from cs.AI) [pdf, other]
Title: Discretization of continuous input spaces in the hippocampal autoencoder
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
[288]  arXiv:2405.14599 (cross-list from cs.CV) [pdf, other]
Title: Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[289]  arXiv:2405.14598 (cross-list from cs.CV) [pdf, other]
Title: Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation
Comments: 10 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[290]  arXiv:2405.14577 (cross-list from cs.CL) [pdf, other]
Title: Representation noising effectively prevents harmful fine-tuning on LLMs
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[291]  arXiv:2405.14574 (cross-list from stat.ML) [pdf, other]
Title: Learning with Fitzpatrick Losses
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[292]  arXiv:2405.14573 (cross-list from cs.AI) [pdf, other]
Title: AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[293]  arXiv:2405.14555 (cross-list from cs.CL) [pdf, other]
Title: Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models
Comments: 9 pages (excluding references), accepted to ACL 2024 Main Conference
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
[294]  arXiv:2405.14545 (cross-list from q-bio.BM) [pdf, other]
Title: A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction
Subjects: Biomolecules (q-bio.BM); Machine Learning (cs.LG)
[295]  arXiv:2405.14540 (cross-list from stat.ML) [pdf, other]
Title: This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[296]  arXiv:2405.14536 (cross-list from q-bio.MN) [pdf, other]
Title: Regressor-free Molecule Generation to Support Drug Response Prediction
Comments: 22 pages, 7 figures, 9 tables,
Subjects: Molecular Networks (q-bio.MN); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[297]  arXiv:2405.14532 (cross-list from stat.ML) [pdf, other]
Title: Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
Comments: 28 pages, 1 figure. Comments are most welcome!
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)
[298]  arXiv:2405.14528 (cross-list from cs.RO) [pdf, other]
Title: Towards Privacy-Aware and Personalised Assistive Robots: A User-Centred Approach
Comments: RSS Pioneers 2024 Research Statement
Subjects: Robotics (cs.RO); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
[299]  arXiv:2405.14507 (cross-list from cs.CL) [pdf, other]
Title: Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[300]  arXiv:2405.14505 (cross-list from cs.CL) [pdf, other]
Title: Explainable automatic industrial carbon footprint estimation from bank transaction classification using natural language processing
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
[301]  arXiv:2405.14494 (cross-list from math.ST) [pdf, other]
Title: Entrywise error bounds for low-rank approximations of kernel matrices
Authors: Alexander Modell
Comments: 28 pages, 3 figures
Subjects: Statistics Theory (math.ST); Machine Learning (cs.LG)
[302]  arXiv:2405.14492 (cross-list from stat.ME) [pdf, other]
Title: Iterative Methods for Full-Scale Gaussian Process Approximations for Large Spatial Data
Subjects: Methodology (stat.ME); Machine Learning (cs.LG); Machine Learning (stat.ML)
[303]  arXiv:2405.14472 (cross-list from eess.SP) [pdf, other]
Title: SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe
Comments: 24 pages, 5 figures
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG)
[304]  arXiv:2405.14467 (cross-list from cs.CV) [pdf, other]
Title: Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation
Comments: 7 pages, to be published in IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2024
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[305]  arXiv:2405.14453 (cross-list from eess.IV) [pdf, other]
Title: Domain-specific augmentations with resolution agnostic self-attention mechanism improves choroid segmentation in optical coherence tomography images
Comments: 13 pages, 2 figures, 8 tables (including supplementary material)
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[306]  arXiv:2405.14436 (cross-list from cs.AI) [pdf, other]
Title: LARS-VSA: A Vector Symbolic Architecture For Learning with Abstract Rules
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[307]  arXiv:2405.14428 (cross-list from cs.CL) [pdf, other]
Title: Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[308]  arXiv:2405.14392 (cross-list from stat.ME) [pdf, other]
Title: Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows
Subjects: Methodology (stat.ME); Machine Learning (cs.LG); Machine Learning (stat.ML)
[309]  arXiv:2405.14374 (cross-list from stat.ML) [pdf, other]
Title: State-Constrained Offline Reinforcement Learning
Subjects: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[310]  arXiv:2405.14366 (cross-list from cs.CL) [pdf, other]
Title: MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Comments: Tech report
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[311]  arXiv:2405.14335 (cross-list from stat.ML) [pdf, other]
Title: Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[312]  arXiv:2405.14331 (cross-list from cs.CV) [pdf, other]
Title: LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
Comments: Work in the review process. The code will be available upon acceptance
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[313]  arXiv:2405.14318 (cross-list from cs.CV) [pdf, other]
Title: Adaptive Rentention & Correction for Continual Learning
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[314]  arXiv:2405.14314 (cross-list from cs.AI) [pdf, other]
Title: Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
Comments: The first two authors contributed equally
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Robotics (cs.RO)
[315]  arXiv:2405.14302 (cross-list from math.AT) [pdf, other]
Title: Graphcode: Learning from multiparameter persistent homology using graph neural networks
Subjects: Algebraic Topology (math.AT); Machine Learning (cs.LG)
[316]  arXiv:2405.14285 (cross-list from stat.ML) [pdf, other]
Title: Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
Comments: Preprint
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Optimization and Control (math.OC)
[317]  arXiv:2405.14244 (cross-list from cs.AI) [pdf, other]
Title: Tell my why: Training preferences-based RL with human preferences and step-level explanations
Authors: Jakob Karalus
Subjects: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
[318]  arXiv:2405.14233 (cross-list from cs.CL) [pdf, other]
Title: Language processing in humans and computers
Authors: Dusko Pavlovic
Comments: 100 pages, 64 figures; lecture notes, book draft
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Logic in Computer Science (cs.LO)
[319]  arXiv:2405.14205 (cross-list from cs.CL) [pdf, other]
Title: Agent Planning with World Knowledge Model
Comments: Work in progress
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
[320]  arXiv:2405.14199 (cross-list from cs.RO) [pdf, other]
Title: Adaptive Teaching in Heterogeneous Agents: Balancing Surprise in Sparse Reward Scenarios
Comments: To be published in L4DC 2024, 10 pages, 5 figures
Subjects: Robotics (cs.RO); Machine Learning (cs.LG)
[321]  arXiv:2405.14194 (cross-list from cs.SI) [pdf, other]
Title: Graphlets correct for the topological information missed by random walks
Subjects: Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG)
[322]  arXiv:2405.14161 (cross-list from cs.CL) [pdf, other]
Title: Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
Comments: 23 pages, Preprint
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[323]  arXiv:2405.14139 (cross-list from q-bio.NC) [pdf, other]
Title: Contribute to balance, wire in accordance: Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule
Subjects: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
[324]  arXiv:2405.14131 (cross-list from stat.ML) [pdf, other]
Title: Statistical Advantages of Perturbing Cosine Router in Sparse Mixture of Experts
Comments: 44 pages, 2 figures
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[325]  arXiv:2405.14128 (cross-list from cs.RO) [pdf, other]
Title: Transformers for Image-Goal Navigation
Subjects: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[326]  arXiv:2405.14116 (cross-list from cs.RO) [pdf, other]
Title: Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction
Subjects: Robotics (cs.RO); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
[327]  arXiv:2405.14115 (cross-list from cs.CV) [pdf, other]
Title: Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers
Comments: 16 pages, 4 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[328]  arXiv:2405.14106 (cross-list from cs.CR) [pdf, other]
Title: Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
[329]  arXiv:2405.14105 (cross-list from cs.DC) [pdf, other]
Title: Distributed Speculative Inference of Large Language Models
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
[330]  arXiv:2405.14101 (cross-list from cs.CV) [pdf, other]
Title: Enhancing Image Layout Control with Loss-Guided Diffusion Models
Subjects: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Machine Learning (cs.LG)
[331]  arXiv:2405.14078 (cross-list from cs.AI) [pdf, ps, other]
Title: A finite time analysis of distributed Q-learning
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
[332]  arXiv:2405.14075 (cross-list from cs.CL) [pdf, other]
Title: $T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models
Comments: 10 pages, 5 figures
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[333]  arXiv:2405.14064 (cross-list from stat.ML) [pdf, other]
Title: Building a stable classifier with the inflated argmax
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)
[334]  arXiv:2405.14062 (cross-list from cs.AI) [pdf, other]
Title: ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
Comments: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[335]  arXiv:2405.14061 (cross-list from cs.AI) [pdf, other]
Title: Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
[336]  arXiv:2405.14058 (cross-list from cs.AI) [pdf, other]
Title: Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)
[337]  arXiv:2405.14039 (cross-list from cs.CL) [pdf, other]
Title: Trajectory Volatility for Out-of-Distribution Detection in Mathematical Reasoning
Comments: 27 pages, 6 figures, 12 tables
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[338]  arXiv:2405.14038 (cross-list from stat.ML) [pdf, other]
Title: FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits
Comments: 28 pages, 1 figure
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)
[339]  arXiv:2405.14014 (cross-list from cs.CV) [pdf, other]
Title: RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
Comments: 16 pages, 3 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
[340]  arXiv:2405.14009 (cross-list from cs.DC) [pdf, other]
Title: SlipStream: Adapting Pipelines for Distributed Training of Large DNNs Amid Failures
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
[341]  arXiv:2405.13997 (cross-list from stat.ML) [pdf, other]
Title: Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
Comments: 31 pages, 2 figures. arXiv admin note: text overlap with arXiv:2402.02952
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[342]  arXiv:2405.13993 (cross-list from cs.CV) [pdf, other]
Title: AutoLCZ: Towards Automatized Local Climate Zone Mapping from Rule-Based Remote Sensing
Comments: accepted at 2024 IGARSS
Subjects: Computer Vision and Pattern Recognition (cs.CV); Computational Engineering, Finance, and Science (cs.CE); Information Retrieval (cs.IR); Machine Learning (cs.LG)
[343]  arXiv:2405.13992 (cross-list from math.OC) [pdf, other]
Title: Learning Cut Generating Functions for Integer Programming
Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG)
[344]  arXiv:2405.13976 (cross-list from cs.NE) [pdf, other]
Title: EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networks
Comments: 11 pages, 6 figures, submitted to IEEE Transactions on Neural Networks and Learning Systems
Subjects: Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG)
[345]  arXiv:2405.13969 (cross-list from cs.RO) [pdf, other]
Title: Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space
Comments: Accepted for publication in IEEE Transactions on Intelligent Vehicles
Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)
[346]  arXiv:2405.13962 (cross-list from stat.ML) [pdf, other]
Title: Learning heavy-tailed distributions with Wasserstein-proximal-regularized $α$-divergences
Comments: 23 pages, 7 figures
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[347]  arXiv:2405.13960 (cross-list from cs.AI) [pdf, other]
Title: Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[348]  arXiv:2405.13950 (cross-list from stat.ML) [pdf, other]
Title: Actor-critic algorithms for fiber sampling problems
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[349]  arXiv:2405.13944 (cross-list from math.OC) [pdf, other]
Title: A Survey on Design-space Dimensionality Reduction Methods for Shape Optimization
Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG)
[350]  arXiv:2405.13939 (cross-list from quant-ph) [pdf, other]
Title: Principal eigenstate classical shadows
Comments: 38 pages
Subjects: Quantum Physics (quant-ph); Information Theory (cs.IT); Machine Learning (cs.LG)
[351]  arXiv:2405.13931 (cross-list from cs.CE) [pdf, other]
Title: A Methodology to Identify Physical or Computational Experiment Conditions for Uncertainty Mitigation
Subjects: Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
[352]  arXiv:2405.13919 (cross-list from cs.GT) [pdf, ps, other]
Title: Fair Online Bilateral Trade
Subjects: Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG)
[353]  arXiv:2405.13912 (cross-list from math.ST) [pdf, other]
Title: Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
Subjects: Statistics Theory (math.ST); Information Theory (cs.IT); Machine Learning (cs.LG); Probability (math.PR); Machine Learning (stat.ML)
[354]  arXiv:2405.13901 (cross-list from cs.CV) [pdf, other]
Title: DCT-Based Decorrelated Attention for Vision Transformers
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Signal Processing (eess.SP)
[355]  arXiv:2405.13899 (cross-list from stat.ML) [pdf, ps, other]
Title: Symmetric Linear Bandits with Hidden Symmetry
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[356]  arXiv:2405.13879 (cross-list from cs.GT) [pdf, other]
Title: FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Comments: 18 pages, 5 figures
Subjects: Computer Science and Game Theory (cs.GT); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Theoretical Economics (econ.TH)
[357]  arXiv:2405.13863 (cross-list from cs.AI) [pdf, other]
Title: Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[358]  arXiv:2405.13858 (cross-list from cs.DC) [pdf, other]
Title: Carbon Connect: An Ecosystem for Sustainable Computing
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Hardware Architecture (cs.AR); Emerging Technologies (cs.ET); Machine Learning (cs.LG)
[359]  arXiv:2405.13854 (cross-list from cond-mat.stat-mech) [pdf, other]
Title: On the dynamics of convolutional recurrent neural networks near their critical point
Subjects: Statistical Mechanics (cond-mat.stat-mech); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
[360]  arXiv:2405.13850 (cross-list from physics.comp-ph) [pdf, other]
Title: Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks
Subjects: Computational Physics (physics.comp-ph); Machine Learning (cs.LG); Fluid Dynamics (physics.flu-dyn)
[361]  arXiv:2405.13846 (cross-list from stat.ML) [pdf, other]
Title: Regression Trees Know Calculus
Authors: Nathan Wycoff
Comments: Comments very welcome!
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[362]  arXiv:2405.13832 (cross-list from cs.CR) [pdf, other]
Title: Federated Learning in Healthcare: Model Misconducts, Security, Challenges, Applications, and Future Research Directions -- A Systematic Review
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[363]  arXiv:2405.13818 (cross-list from eess.SY) [pdf, other]
Title: Identifiability of Differential-Algebraic Systems
Comments: Codes available at this https URL
Subjects: Systems and Control (eess.SY); Machine Learning (cs.LG); Dynamical Systems (math.DS); Optimization and Control (math.OC)
[364]  arXiv:2405.13805 (cross-list from eess.IV) [pdf, other]
Title: Perceptual Fairness in Image Restoration
Subjects: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[365]  arXiv:2405.13794 (cross-list from stat.ML) [pdf, other]
Title: Conditioning diffusion models by explicit forward-backward bridging
Comments: 24 pages, 12 figures
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Computation (stat.CO); Methodology (stat.ME)
[366]  arXiv:2405.13779 (cross-list from cs.CV) [pdf, other]
Title: Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[367]  arXiv:2405.13771 (cross-list from eess.IV) [pdf, other]
Title: Multi-Dataset Multi-Task Learning for COVID-19 Prognosis
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[368]  arXiv:2405.13762 (cross-list from cs.CV) [pdf, other]
Title: A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[369]  arXiv:2405.13758 (cross-list from cs.CV) [pdf, other]
Title: Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks
Comments: 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR)
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[370]  arXiv:2405.13757 (cross-list from eess.IV) [pdf, other]
Title: A label-free and data-free training strategy for vasculature segmentation in serial sectioning OCT data
Comments: 5 Pages, 2 figures. Accepted by Medical Imaging with Deep Learning
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[371]  arXiv:2405.13740 (cross-list from cs.SE) [pdf, other]
Title: Mining Action Rules for Defect Reduction Planning
Subjects: Software Engineering (cs.SE); Machine Learning (cs.LG)
[372]  arXiv:2405.13735 (cross-list from eess.SY) [pdf, other]
Title: Transfer of Safety Controllers Through Learning Deep Inverse Dynamics Model
Comments: Extended Version, submitted to 2024 ADHS
Subjects: Systems and Control (eess.SY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[373]  arXiv:2405.13731 (cross-list from stat.ML) [pdf, other]
Title: Control, Transport and Sampling: Towards Better Loss Design
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Computation (stat.CO)
[374]  arXiv:2405.13710 (cross-list from eess.IV) [pdf, other]
Title: Optimizing Lymphocyte Detection in Breast Cancer Whole Slide Imaging through Data-Centric Strategies
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[375]  arXiv:2405.13670 (cross-list from cs.SI) [pdf, ps, other]
Title: GNN-based Anomaly Detection for Encoded Network Traffic
Subjects: Social and Information Networks (cs.SI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)
[376]  arXiv:2405.13640 (cross-list from cs.CL) [pdf, other]
Title: Knowledge Graph Reasoning with Self-supervised Reinforcement Learning
Comments: 17 pages, 11 figures
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[377]  arXiv:2405.13637 (cross-list from cs.CV) [pdf, other]
Title: Curriculum Direct Preference Optimization for Diffusion and Consistency Models
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[378]  arXiv:2405.13602 (cross-list from cs.AI) [pdf, other]
Title: COTET: Cross-view Optimal Transport for Knowledge Graph Entity Typing
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
[379]  arXiv:2405.13587 (cross-list from stat.ML) [pdf, other]
Title: Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Probability (math.PR)
[380]  arXiv:2405.13574 (cross-list from stat.CO) [pdf, other]
Title: Reinforcement Learning for Adaptive MCMC
Subjects: Computation (stat.CO); Machine Learning (cs.LG)
[381]  arXiv:2405.13568 (cross-list from cs.CR) [pdf, other]
Title: CPE-Identifier: Automated CPE identification and CVE summaries annotation with Deep Learning and NLP
Comments: International Conference on Information Systems Security and Privacy 2024
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
[382]  arXiv:2405.13541 (cross-list from cs.CL) [pdf, other]
Title: Annotation-Efficient Preference Optimization for Language Model Alignment
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[383]  arXiv:2405.13516 (cross-list from cs.CL) [pdf, other]
Title: LIRE: listwise reward enhancement for preference alignment
Comments: Accepted by ACL 2024 Findings
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[384]  arXiv:2405.13515 (cross-list from quant-ph) [pdf, other]
Title: Multi-Scale Feature Fusion Quantum Depthwise Convolutional Neural Networks for Text Classification
Subjects: Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[385]  arXiv:2405.13512 (cross-list from cs.SY) [pdf, other]
Title: Coverage Path Planning for Thermal Interface Materials
Subjects: Systems and Control (eess.SY); Machine Learning (cs.LG)
[386]  arXiv:2405.13481 (cross-list from stat.ML) [pdf, other]
Title: Locally Private Estimation with Public Features
Subjects: Machine Learning (stat.ML); Cryptography and Security (cs.CR); Machine Learning (cs.LG)
[387]  arXiv:2405.13469 (cross-list from astro-ph.EP) [pdf, other]
Title: Machine Learning for Exoplanet Detection in High-Contrast Spectroscopy: Revealing Exoplanets by Leveraging Hidden Molecular Signatures in Cross-Correlated Spectra with Convolutional Neural Networks
Comments: 27 pages, 24 figures. Submitted for publication in A&A January 2, 2024. After first iteration with the referee, resubmitted May 17, 2024
Subjects: Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG); Applications (stat.AP)
[388]  arXiv:2405.13468 (cross-list from astro-ph.EP) [pdf, other]
Title: Machine learning for exoplanet detection in high-contrast spectroscopy Combining cross correlation maps and deep learning on medium-resolution integral-field spectra
Comments: Accepted for publication in A&A on 23/04/2024. Total 15 pages of text, 7 figures
Subjects: Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG); Applied Physics (physics.app-ph); Data Analysis, Statistics and Probability (physics.data-an)
[389]  arXiv:2405.13456 (cross-list from stat.ML) [pdf, other]
Title: Deep linear networks for regression are implicitly regularized towards flat minima
Comments: 46 pages, 4 figures
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[390]  arXiv:2405.13413 (cross-list from cs.IT) [pdf, other]
Title: Boosted Neural Decoders: Achieving Extreme Reliability of LDPC Codes for 6G Networks
Comments: 12 pages, 11 figures
Subjects: Information Theory (cs.IT); Machine Learning (cs.LG); Signal Processing (eess.SP)
[391]  arXiv:2405.13370 (cross-list from eess.IV) [pdf, other]
Title: Low-Resolution Chest X-ray Classification via Knowledge Distillation and Multi-task Learning
Comments: IEEE ISBI 2024
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[392]  arXiv:2405.13362 (cross-list from cs.IR) [pdf, ps, other]
Title: Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG)
[393]  arXiv:2405.13360 (cross-list from cs.CV) [pdf, other]
Title: How to Trace Latent Generative Model Generated Images without Artificial Watermark?
Comments: ICML 2024
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[394]  arXiv:2405.13350 (cross-list from cs.CL) [pdf, other]
Title: Efficacy of ByteT5 in Multilingual Translation of Biblical Texts for Underrepresented Languages
Comments: LXAI Workshop at the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[395]  arXiv:2405.13345 (cross-list from cs.RO) [pdf, other]
Title: Autonomous Algorithm for Training Autonomous Vehicles with Minimal Human Intervention
Comments: 8 pages, 6 figures, 2 tables, conference
Subjects: Robotics (cs.RO); Machine Learning (cs.LG)
[396]  arXiv:2405.13319 (cross-list from cs.CL) [pdf, other]
Title: ''You should probably read this'': Hedge Detection in Text
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[397]  arXiv:2405.13304 (cross-list from eess.IV) [pdf, other]
Title: Hybrid Multihead Attentive Unet-3D for Brain Tumor Segmentation
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[398]  arXiv:2405.13302 (cross-list from stat.ML) [pdf, other]
Title: Accelerated Evaluation of Ollivier-Ricci Curvature Lower Bounds: Bridging Theory and Computation
Subjects: Machine Learning (stat.ML); Discrete Mathematics (cs.DM); Machine Learning (cs.LG); Optimization and Control (math.OC)
[399]  arXiv:2405.13285 (cross-list from cs.CV) [pdf, ps, other]
Title: Enhancing Active Learning for Sentinel 2 Imagery through Contrastive Learning and Uncertainty Estimation
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[400]  arXiv:2405.13247 (cross-list from astro-ph.EP) [pdf, other]
Title: Improving Earth-like planet detection in radial velocity using deep learning
Comments: Accepted for publication in A&A
Subjects: Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG)
[401]  arXiv:2405.13238 (cross-list from cs.IR) [pdf, ps, other]
Title: Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG)
[402]  arXiv:2405.13235 (cross-list from eess.IV) [pdf, other]
Title: Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos
Comments: Early Acceptance for MICCAI 2024
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[403]  arXiv:2405.13226 (cross-list from cs.CL) [pdf, other]
Title: Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[404]  arXiv:2405.13209 (cross-list from cs.CL) [pdf, other]
Title: Investigating Symbolic Capabilities of Large Language Models
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[405]  arXiv:2405.13202 (cross-list from cs.CV) [pdf, other]
Title: Empowering Urban Traffic Management: Elevated 3D LiDAR for Data Collection and Advanced Object Detection Analysis
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[406]  arXiv:2405.13181 (cross-list from cs.CL) [pdf, other]
Title: Comparative Analysis of Different Efficient Fine Tuning Methods of Large Language Models (LLMs) in Low-Resource Setting
Comments: 9 pages of main paper, 1 page of references, 6 appendix pages, 11 figures, 18 tables
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[407]  arXiv:2405.13180 (cross-list from eess.SP) [pdf, other]
Title: Data Assimilation with Machine Learning Surrogate Models: A Case Study with FourCastNet
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG); Chaotic Dynamics (nlin.CD); Atmospheric and Oceanic Physics (physics.ao-ph); Applications (stat.AP)
[408]  arXiv:2405.13160 (cross-list from stat.ML) [pdf, other]
Title: Borrowing Strength in Distributionally Robust Optimization via Hierarchical Dirichlet Processes
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[409]  arXiv:2405.13149 (cross-list from stat.ML) [pdf, other]
Title: Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulation
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Numerical Analysis (math.NA); Probability (math.PR); Computation (stat.CO)
[410]  arXiv:2405.13147 (cross-list from cs.CR) [pdf, other]
Title: A novel reliability attack of Physical Unclonable Functions
Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
[411]  arXiv:2405.13140 (cross-list from math.ST) [pdf, ps, other]
Title: On Convergence of the Alternating Directions SGHMC Algorithm
Subjects: Statistics Theory (math.ST); Machine Learning (cs.LG); Probability (math.PR)
[412]  arXiv:2405.13135 (cross-list from cs.CL) [pdf, other]
Title: Dataset Mention Extraction in Scientific Articles Using Bi-LSTM-CRF Model
Journal-ref: Rich Search and Discovery for Research Datasets, 2020, 158-165
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[413]  arXiv:2405.13130 (cross-list from cs.RO) [pdf, other]
Title: Pure Planning to Pure Policies and In Between with a Recursive Tree Planner
Comments: 30 pages, 15 figures, 3 tables
Subjects: Robotics (cs.RO); Machine Learning (cs.LG)
[414]  arXiv:2405.13102 (cross-list from cs.GT) [pdf, ps, other]
Title: Trading Volume Maximization with Online Learning
Subjects: Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG); Computational Finance (q-fin.CP)
[415]  arXiv:2405.13094 (cross-list from cs.SI) [pdf, other]
Title: KPG: Key Propagation Graph Generator for Rumor Detection based on Reinforcement Learning
Subjects: Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[416]  arXiv:2405.13092 (cross-list from cs.AI) [pdf, other]
Title: CausalPlayground: Addressing Data-Generation Requirements in Cutting-Edge Causality Research
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[417]  arXiv:2405.13080 (cross-list from cs.CR) [pdf, other]
Title: EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection
Comments: 18 pages, 12 figures
Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
[418]  arXiv:2405.13076 (cross-list from q-fin.ST) [pdf, ps, other]
Title: A K-means Algorithm for Financial Market Risk Forecasting
Subjects: Statistical Finance (q-fin.ST); Machine Learning (cs.LG)
[419]  arXiv:2405.13073 (cross-list from stat.ML) [pdf, other]
Title: A graph-structured distance for heterogeneous datasets with meta variables
Comments: 25 pages (without references), 5 figures, data and scripts available at this https URL
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[420]  arXiv:2405.13068 (cross-list from cs.CR) [pdf, other]
Title: Lockpicking LLMs: A Logit-Based Jailbreak Using Token-level Manipulation
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[421]  arXiv:2405.13062 (cross-list from cs.CR) [pdf, other]
Title: StatAvg: Mitigating Data Heterogeneity in Federated Learning for Intrusion Detection Systems
Comments: 10 pages, 8 figures
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
[422]  arXiv:2405.13058 (cross-list from cs.SE) [pdf, other]
Title: The AI Community Building the Future? A Quantitative Analysis of Development Activity on Hugging Face Hub
Comments: 27 pages, 5 figures, 9 tables
Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
[423]  arXiv:2405.13052 (cross-list from cs.HC) [pdf, other]
Title: Large Language Models Can Infer Personality from Free-Form User Interactions
Subjects: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY); Machine Learning (cs.LG)
[424]  arXiv:2405.13046 (cross-list from cs.CL) [pdf, other]
Title: LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Comments: Submitted and accepted at ICML 2024
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[425]  arXiv:2405.13044 (cross-list from cs.CL) [pdf, other]
Title: Case-Based Reasoning Approach for Solving Financial Question Answering
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
[426]  arXiv:2405.13031 (cross-list from cs.CL) [pdf, other]
Title: A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text
Comments: Submitted to ECML/PKDD 2024
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[427]  arXiv:2405.13022 (cross-list from cs.CL) [pdf, other]
Title: LLMs can learn self-restraint through iterative self-reflection
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[428]  arXiv:2405.13017 (cross-list from cs.CL) [pdf, other]
Title: A Systematic Analysis on the Temporal Generalization of Language Models in Social Media
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[429]  arXiv:2405.13007 (cross-list from cs.CL) [pdf, other]
Title: News Recommendation with Category Description by a Large Language Model
Comments: 5 pages, 5 figures
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)

Wed, 22 May 2024

[430]  arXiv:2405.12981 [pdf, other]
Title: Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
[431]  arXiv:2405.12969 [pdf, other]
Title: Can We Treat Noisy Labels as Accurate?
Comments: 10 pages
Subjects: Machine Learning (cs.LG)
[432]  arXiv:2405.12961 [pdf, other]
Title: Energy Rank Alignment: Using Preference Optimization to Search Chemical Space at Scale
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Chemical Physics (physics.chem-ph); Quantitative Methods (q-bio.QM)
[433]  arXiv:2405.12958 [pdf, ps, other]
Title: Online Learning of Halfspaces with Massart Noise
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Statistics Theory (math.ST); Machine Learning (stat.ML)
[434]  arXiv:2405.12954 [pdf, other]
Title: A Method on Searching Better Activation Functions
Comments: 16 pages,3 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[435]  arXiv:2405.12952 [pdf, ps, other]
Title: Truncated Variance Reduced Value Iteration
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Optimization and Control (math.OC)
[436]  arXiv:2405.12926 [pdf, other]
Title: Trusting Fair Data: Leveraging Quality in Fairness-Driven Data Removal Techniques
Subjects: Machine Learning (cs.LG)
[437]  arXiv:2405.12888 [pdf, other]
Title: Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
Comments: Accepted to ICML 2024
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[438]  arXiv:2405.12868 [pdf, other]
Title: Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
Comments: The paper has been published to the conference of NeurIPS 2023
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[439]  arXiv:2405.12832 [pdf, other]
Title: Wav-KAN: Wavelet Kolmogorov-Arnold Networks
Comments: Work in progress
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP); Machine Learning (stat.ML)
[440]  arXiv:2405.12807 [pdf, other]
Title: FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information
Authors: Dongseong Hwang
Comments: 19 pages, 1 figures, 5 tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Information Theory (cs.IT)
[441]  arXiv:2405.12802 [pdf, other]
Title: Stochastic Inference of Plate Bending from Heterogeneous Data: Physics-informed Gaussian Processes via Kirchhoff-Love Theory
Comments: 24 pages, 11 figures
Subjects: Machine Learning (cs.LG); Data Analysis, Statistics and Probability (physics.data-an)
[442]  arXiv:2405.12779 [pdf, ps, other]
Title: Transformer in Touch: A Survey
Comments: 27 pages, 2 tables, 5 figures, accepted by ICIC 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[443]  arXiv:2405.12774 [pdf, ps, other]
Title: Blind Separation of Vibration Sources using Deep Learning and Deconvolution
Comments: 20 pages, 13 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS); Signal Processing (eess.SP)
[444]  arXiv:2405.12756 [pdf, other]
Title: Parallel Algorithm for Optimal Threshold Labeling of Ordinal Regression Methods
Subjects: Machine Learning (cs.LG)
[445]  arXiv:2405.12755 [pdf, other]
Title: Progress Measures for Grokking on Real-world Datasets
Authors: Satvik Golechha
Comments: 5 pages
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[446]  arXiv:2405.12739 [pdf, other]
Title: SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling
Subjects: Machine Learning (cs.LG)
[447]  arXiv:2405.12711 [pdf, other]
Title: A Masked Semi-Supervised Learning Approach for Otago Micro Labels Recognition
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[448]  arXiv:2405.12658 [pdf, other]
Title: Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations
Comments: Accepted for the 40th Conference on Uncertainty in Artificial Intelligence (UAI 2024)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[449]  arXiv:2405.12638 [pdf, ps, other]
Title: Multiscale lubrication simulation based on fourier feature networks with trainable frequency
Subjects: Machine Learning (cs.LG)
[450]  arXiv:2405.12615 [pdf, other]
Title: Learning Causal Dynamics Models in Object-Oriented Environments
Comments: Accepted by ICML 2024. 42 Pages
Subjects: Machine Learning (cs.LG)
[451]  arXiv:2405.12590 [pdf, other]
Title: Maverick-Aware Shapley Valuation for Client Selection in Federated Learning
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
[452]  arXiv:2405.12521 [pdf, other]
Title: Unleash Graph Neural Networks from Heavy Tuning
Subjects: Machine Learning (cs.LG)
[453]  arXiv:2405.12519 [pdf, other]
Title: MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
Comments: arXiv admin note: text overlap with arXiv:2405.08419
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
[454]  arXiv:2405.12502 [pdf, other]
Title: EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[455]  arXiv:2405.12500 [pdf, ps, other]
Title: Entropic associative memory for real world images
Subjects: Machine Learning (cs.LG)
[456]  arXiv:2405.12493 [pdf, other]
Title: Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
Subjects: Machine Learning (cs.LG)
[457]  arXiv:2405.12489 [pdf, other]
Title: Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[458]  arXiv:2405.12475 [pdf, other]
Title: GASE: Graph Attention Sampling with Edges Fusion for Solving Vehicle Routing Problems
Comments: 24 pages, 5figures, 4 tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[459]  arXiv:2405.12474 [pdf, other]
Title: How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
Comments: arXiv admin note: substantial text overlap with arXiv:2311.18177
Subjects: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
[460]  arXiv:2405.12465 [pdf, other]
Title: A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains
Subjects: Machine Learning (cs.LG)
[461]  arXiv:2405.12462 [src]
Title: Boosting X-formers with Structured Matrix for Long Sequence Time Series Forecasting
Comments: We believe this work is premature and requires further study
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[462]  arXiv:2405.12459 [pdf, other]
Title: PLM4Traj: Cognizing Movement Patterns and Travel Purposes from Trajectories with Pre-trained Language Models
Subjects: Machine Learning (cs.LG)
[463]  arXiv:2405.12452 [pdf, other]
Title: Prompt-Enhanced Spatio-Temporal Graph Transfer Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[464]  arXiv:2405.12443 [pdf, other]
Title: FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropagation
Comments: Accepted at the Great Lakes Symposium on VLSI 2024
Subjects: Machine Learning (cs.LG)
[465]  arXiv:2405.12439 [pdf, other]
Title: No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS)
[466]  arXiv:2405.12427 [pdf, other]
Title: Deep learning approaches to indoor wireless channel estimation for low-power communication
Subjects: Machine Learning (cs.LG)
[467]  arXiv:2405.12421 [pdf, other]
Title: A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
Comments: ICML 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
[468]  arXiv:2405.12412 [pdf, other]
Title: On Measuring Calibration of Discrete Probabilistic Neural Networks
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[469]  arXiv:2405.12399 [pdf, other]
Title: Diffusion for World Modeling: Visual Details Matter in Atari
Comments: 25 pages, 11 figures, 10 tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[470]  arXiv:2405.12398 [pdf, other]
Title: ASMR: Activation-sharing Multi-resolution Coordinate Networks For Efficient Inference
Comments: ICLR 2024 (v3: 21 pages, 11 figures, Project Page: this https URL)
Subjects: Machine Learning (cs.LG)
[471]  arXiv:2405.12387 [pdf, other]
Title: Conformal Counterfactual Inference under Hidden Confounding
Comments: Published in SIGKDD'24
Subjects: Machine Learning (cs.LG)
[472]  arXiv:2405.12382 [pdf, other]
Title: Stochastic Reservoir Computers
Comments: 30 pages, 6 figures
Subjects: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Systems and Control (eess.SY); Adaptation and Self-Organizing Systems (nlin.AO); Machine Learning (stat.ML)
[473]  arXiv:2405.12380 [pdf, other]
Title: Large scale scattering using fast solvers based on neural operators
Subjects: Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
[474]  arXiv:2405.12372 [pdf, other]
Title: DispaRisk: Assessing and Interpreting Disparity Risks in Datasets
Subjects: Machine Learning (cs.LG)
[475]  arXiv:2405.12355 [pdf, other]
Title: Investigating the Impact of Choice on Deep Reinforcement Learning for Space Controls
Subjects: Machine Learning (cs.LG); Systems and Control (eess.SY)
[476]  arXiv:2405.12353 [pdf, other]
Title: TinyM$^2$Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment
Comments: Accepted at AAAI 2024 Workshop SAI
Subjects: Machine Learning (cs.LG)
[477]  arXiv:2405.12340 [pdf, other]
Title: Cascade-based Randomization for Inferring Causal Effects under Diffusion Interference
Subjects: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
[478]  arXiv:2405.12326 [pdf, other]
Title: Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligence
Authors: José Daniel Pascual-Triana (1), Alberto Fernández (1), Javier Del Ser (1, 2 and 3), Francisco Herrera (1) ((1) Andalusian Institute of Data Science and Computational Intelligence (DASCI), University of Granada, Granada, Spain, (2) TECNALIA, Basque Research & Technology Alliance (BRTA), Derio, Spain, (3) University of the Basque Country (UPV/EHU), Bilbao, Spain)
Comments: 21 pages, 6 figures. Submitted to Information Sciences
Subjects: Machine Learning (cs.LG)
[479]  arXiv:2405.12319 [pdf, other]
Title: Dynamic Line Rating using Hyper-local Weather Predictions: A Machine Learning Approach
Comments: 15 pages and planning to submit it to IEEE Access
Subjects: Machine Learning (cs.LG); Systems and Control (eess.SY)
[480]  arXiv:2405.12312 [pdf, other]
Title: A Principled Approach for a New Bias Measure
Subjects: Machine Learning (cs.LG); Computers and Society (cs.CY)
[481]  arXiv:2405.12308 [pdf, other]
Title: Continual Deep Reinforcement Learning for Decentralized Satellite Routing
Comments: 30 pages, 11 figures
Subjects: Machine Learning (cs.LG); Information Theory (cs.IT)
[482]  arXiv:2405.12299 [pdf, other]
Title: Perturbing the Gradient for Alleviating Meta Overfitting
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[483]  arXiv:2405.12295 [pdf, other]
Title: Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks
Comments: arXiv admin note: text overlap with arXiv:2112.08331 by other authors
Subjects: Machine Learning (cs.LG)
[484]  arXiv:2405.12264 [pdf, ps, other]
Title: Directed Metric Structures arising in Large Language Models
Subjects: Machine Learning (cs.LG); Category Theory (math.CT); Metric Geometry (math.MG)
[485]  arXiv:2405.12262 [pdf, other]
Title: Prompt Learning for Generalized Vehicle Routing
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[486]  arXiv:2405.12261 [pdf, ps, other]
Title: EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[487]  arXiv:2405.12259 [pdf, other]
Title: Generalization Ability of Feature-based Performance Prediction Models: A Statistical Analysis across Benchmarks
Comments: To appear in the Proc. of the 2024 IEEE World Congress on Computational - Congress on Evolutionary Computation
Subjects: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
[488]  arXiv:2405.12250 [pdf, other]
Title: Your Transformer is Secretly Linear
Comments: 9 pages, 9 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[489]  arXiv:2405.12241 [pdf, other]
Title: Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[490]  arXiv:2405.12237 [pdf, other]
Title: EKM: An exact, polynomial-time algorithm for the $K$-medoids problem
Authors: Xi He, Max A. Little
Subjects: Machine Learning (cs.LG); Computation (stat.CO); Machine Learning (stat.ML)
[491]  arXiv:2405.12235 [pdf, ps, other]
Title: Hypergraph: A Unified and Uniform Definition with Application to Chemical Hypergraph
Authors: Daniel T. Chang
Subjects: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
[492]  arXiv:2405.12228 [pdf, other]
Title: Fast Stochastic Policy Gradient: Negative Momentum for Reinforcement Learning
Subjects: Machine Learning (cs.LG)
[493]  arXiv:2405.12965 (cross-list from astro-ph.CO) [pdf, other]
Title: The future of cosmological likelihood-based inference: accelerated high-dimensional parameter estimation and model comparison
Comments: 13 pages, 6 figures. Codes available at this https URL, this https URL, this https URL
Subjects: Cosmology and Nongalactic Astrophysics (astro-ph.CO); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG)
[494]  arXiv:2405.12963 (cross-list from eess.IV) [pdf, ps, other]
Title: Comprehensive Multimodal Deep Learning Survival Prediction Enabled by a Transformer Architecture: A Multicenter Study in Glioblastoma
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[495]  arXiv:2405.12957 (cross-list from cs.SD) [pdf, other]
Title: Enhancing the analysis of murine neonatal ultrasonic vocalizations: Development, evaluation, and application of different mathematical models
Subjects: Sound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
[496]  arXiv:2405.12946 (cross-list from cs.HC) [pdf, other]
Title: Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs
Subjects: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
[497]  arXiv:2405.12940 (cross-list from stat.ML) [pdf, other]
Title: Learning the Infinitesimal Generator of Stochastic Diffusion Processes
Comments: 38 pages, 3 figures
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Probability (math.PR)
[498]  arXiv:2405.12933 (cross-list from cs.CL) [pdf, other]
Title: Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
Comments: ACL 2024, long paper
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[499]  arXiv:2405.12930 (cross-list from cs.CV) [pdf, other]
Title: Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation
Comments: Pytorch-Wildlife is available at this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[500]  arXiv:2405.12910 (cross-list from cs.CL) [pdf, ps, other]
Title: Topic Modelling Case Law Using a Large Language Model and a New Taxonomy for UK Law: AI Insights into Summary Judgment
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
[501]  arXiv:2405.12894 (cross-list from cs.DC) [pdf, other]
Title: Decentralized Federated Learning Over Imperfect Communication Channels
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Information Theory (cs.IT); Machine Learning (cs.LG)
[502]  arXiv:2405.12892 (cross-list from cs.IR) [pdf, other]
Title: Retrievable Domain-Sensitive Feature Memory for Multi-Domain Recommendation
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG)
[503]  arXiv:2405.12856 (cross-list from stat.ML) [pdf, other]
Title: LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
Subjects: Machine Learning (stat.ML); Computation and Language (cs.CL); Machine Learning (cs.LG)
[504]  arXiv:2405.12847 (cross-list from cs.IR) [pdf, other]
Title: A Dataset and Baselines for Measuring and Predicting the Music Piece Memorability
Journal-ref: Proceedings of the 24th International Society for Music Information Retrieval Conference, 174-181. Milan, Italy, November 5-9, 2023
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[505]  arXiv:2405.12843 (cross-list from cs.CY) [pdf, other]
Title: OpenCarbonEval: A Unified Carbon Emission Estimation Framework in Large-Scale AI Models
Subjects: Computers and Society (cs.CY); Machine Learning (cs.LG)
[506]  arXiv:2405.12840 (cross-list from cs.IR) [pdf, other]
Title: GotFunding: A grant recommendation system based on scientific articles
Journal-ref: Proceedings of the Association for Information Science and Technology (2020), Volume 57, Issue 1, e323
Subjects: Information Retrieval (cs.IR); Digital Libraries (cs.DL); Machine Learning (cs.LG)
[507]  arXiv:2405.12801 (cross-list from cs.CL) [pdf, other]
Title: Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval
Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG)
[508]  arXiv:2405.12800 (cross-list from cs.RO) [pdf, other]
Title: Deep Reinforcement Learning for Time-Critical Wilderness Search And Rescue Using Drones
Comments: 16 pages, 19 figures. Submitted
Subjects: Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)
[509]  arXiv:2405.12783 (cross-list from stat.ML) [pdf, other]
Title: Epanechnikov Variational Autoencoder
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[510]  arXiv:2405.12781 (cross-list from cs.CV) [pdf, other]
Title: Self-Supervised Modality-Agnostic Pre-Training of Swin Transformers
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[511]  arXiv:2405.12754 (cross-list from astro-ph.SR) [pdf, other]
Title: Neural Operator for Accelerating Coronal Magnetic Field Model
Subjects: Solar and Stellar Astrophysics (astro-ph.SR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Space Physics (physics.space-ph)
[512]  arXiv:2405.12716 (cross-list from cs.AI) [pdf, other]
Title: Reinforcement Learning Enabled Peer-to-Peer Energy Trading for Dairy Farms
Comments: Proc. of the Main Track of 22nd International Conference on Practical Applications of Agents and Multi-Agent Systems, 26th-28th June, 2024, this https URL Includes 6 figures, 1 table and 32 references
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
[513]  arXiv:2405.12705 (cross-list from cs.CV) [pdf, other]
Title: Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting
Comments: Accepted at ICDAR 2024
Subjects: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Machine Learning (cs.LG)
[514]  arXiv:2405.12684 (cross-list from stat.ML) [pdf, ps, other]
Title: Model Free Prediction with Uncertainty Assessment
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[515]  arXiv:2405.12666 (cross-list from cs.SD) [pdf, other]
Title: SYMPLEX: Controllable Symbolic Music Generation using Simplex Diffusion with Vocabulary Priors
Subjects: Sound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
[516]  arXiv:2405.12612 (cross-list from cs.CL) [pdf, other]
Title: Tagengo: A Multilingual Chat Dataset
Authors: Peter Devine
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[517]  arXiv:2405.12584 (cross-list from eess.IV) [pdf, other]
Title: Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?
Comments: 10 pages, 6 figures
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[518]  arXiv:2405.12573 (cross-list from cs.RO) [pdf, other]
Title: EchoPT: A Pretrained Transformer Architecture that Predicts 2D In-Air Sonar Images for Mobile Robotics
Subjects: Robotics (cs.RO); Machine Learning (cs.LG); Signal Processing (eess.SP); Systems and Control (eess.SY)
[519]  arXiv:2405.12553 (cross-list from stat.ML) [pdf, other]
Title: Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
Subjects: Machine Learning (stat.ML); Cryptography and Security (cs.CR); Machine Learning (cs.LG); Statistics Theory (math.ST); Computation (stat.CO)
[520]  arXiv:2405.12531 (cross-list from cs.CV) [pdf, other]
Title: CustomText: Customized Textual Image Generation using Diffusion Models
Comments: Accepted by AI for Content Creation (AI4CC) workshop at CVPR 2024
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[521]  arXiv:2405.12522 (cross-list from cs.CL) [pdf, other]
Title: Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
[522]  arXiv:2405.12463 (cross-list from math.OC) [pdf, other]
Title: Stochastic Learning of Computational Resource Usage as Graph Structured Multimarginal Schrödinger Bridge
Subjects: Optimization and Control (math.OC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY); Machine Learning (stat.ML)
[523]  arXiv:2405.12456 (cross-list from eess.IV) [pdf, other]
Title: Mutual Information Analysis in Multimodal Learning Systems
Comments: 6 pages, 7 figures, IEEE MIPR 2024
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[524]  arXiv:2405.12424 (cross-list from cs.RO) [pdf, other]
Title: Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers
Comments: RSS 2024
Subjects: Robotics (cs.RO); Machine Learning (cs.LG)
[525]  arXiv:2405.12419 (cross-list from cs.CV) [pdf, other]
Title: GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[526]  arXiv:2405.12390 (cross-list from stat.ML) [pdf, other]
Title: A Metric-based Principal Curve Approach for Learning One-dimensional Manifold
Subjects: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Applications (stat.AP)
[527]  arXiv:2405.12386 (cross-list from stat.ML) [pdf, other]
Title: Particle swarm optimization with Applications to Maximum Likelihood Estimation and Penalized Negative Binomial Regression
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Applications (stat.AP); Computation (stat.CO)
[528]  arXiv:2405.12384 (cross-list from cs.CR) [pdf, other]
Title: Vulnerability Detection with Deep Learning
Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
[529]  arXiv:2405.12377 (cross-list from eess.SY) [pdf, ps, other]
Title: Spatio-temporal Attention-based Hidden Physics-informed Neural Network for Remaining Useful Life Prediction
Subjects: Systems and Control (eess.SY); Machine Learning (cs.LG)
[530]  arXiv:2405.12356 (cross-list from physics.bio-ph) [pdf, other]
Title: Coarse-graining conformational dynamics with multi-dimensional generalized Langevin equation: how, when, and why
Subjects: Biological Physics (physics.bio-ph); Machine Learning (cs.LG); Chemical Physics (physics.chem-ph); Data Analysis, Statistics and Probability (physics.data-an)
[531]  arXiv:2405.12354 (cross-list from quant-ph) [pdf, other]
Title: A Study on Optimization Techniques for Variational Quantum Circuits in Reinforcement Learning
Comments: Accepted at QSW 2024
Subjects: Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[532]  arXiv:2405.12327 (cross-list from cs.IR) [pdf, other]
Title: Diversifying by Intent in Recommender Systems
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG)
[533]  arXiv:2405.12317 (cross-list from stat.ML) [pdf, other]
Title: Kernel spectral joint embeddings for high-dimensional noisy datasets using duo-landmark integral operators
Authors: Xiucai Ding, Rong Ma
Comments: 32 pages, 5 figures; comments are welcome
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[534]  arXiv:2405.12309 (cross-list from quant-ph) [pdf, other]
Title: Accurate Learning of Equivariant Quantum Systems from a Single Ground State
Comments: 5 pages, 3 figures
Subjects: Quantum Physics (quant-ph); Machine Learning (cs.LG)
[535]  arXiv:2405.12300 (cross-list from cond-mat.mtrl-sci) [pdf, ps, other]
Title: Integration of Scanning Probe Microscope with High-Performance Computing: fixed-policy and reward-driven workflows implementation
Comments: 16 pages, 7 figures
Subjects: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
[536]  arXiv:2405.12266 (cross-list from cs.CR) [pdf, other]
Title: EGAN: Evolutional GAN for Ransomware Evasion
Journal-ref: 2023 IEEE 48th Conference on Local Computer Networks (LCN), Daytona Beach, FL, USA, 2023, pp. 1-9
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
[537]  arXiv:2405.12258 (cross-list from q-bio.QM) [pdf, ps, other]
Title: Scientific Hypothesis Generation by a Large Language Model: Laboratory Validation in Breast Cancer Treatment
Comments: 20 pages, 7 tables. Supplementary information available
Subjects: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Cell Behavior (q-bio.CB)
[538]  arXiv:2405.12244 (cross-list from physics.soc-ph) [pdf, ps, other]
Title: Real-Time Go-Around Prediction: A case study of JFK airport
Comments: this https URL
Journal-ref: International Conference on Research in Air Transportation (ICRAT2024)
Subjects: Physics and Society (physics.soc-ph); Machine Learning (cs.LG)
[539]  arXiv:2405.12236 (cross-list from cs.AI) [pdf, other]
Title: Fully Distributed Fog Load Balancing with Multi-Agent Reinforcement Learning
Comments: Submitted to IEEE IoTJ with 13 pages, 11 figures, and 3 tables
Subjects: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
[540]  arXiv:2405.12234 (cross-list from stat.ML) [pdf, ps, other]
Title: Joint Prediction Regions for time-series models
Comments: This work is a Master Thesis
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[541]  arXiv:2405.12225 (cross-list from q-bio.QM) [pdf, other]
Title: Unraveling the Autism spectrum heterogeneity: Insights from ABIDE I Database using data/model-driven permutation testing approaches
Comments: 54 pages, 14 figures
Subjects: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Image and Video Processing (eess.IV); Signal Processing (eess.SP)

Tue, 21 May 2024 (showing first 115 of 199 entries)

[542]  arXiv:2405.12207 [pdf, other]
Title: Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
Subjects: Machine Learning (cs.LG); Information Retrieval (cs.IR)
[543]  arXiv:2405.12186 [pdf, other]
Title: Training Data Attribution via Approximate Unrolled Differentiation
Subjects: Machine Learning (cs.LG)
[544]  arXiv:2405.12183 [pdf, other]
Title: Multi-order Graph Clustering with Adaptive Node-level Weight Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[545]  arXiv:2405.12179 [pdf, other]
Title: Building Temporal Kernels with Orthogonal Polynomials
Comments: 16 pages, 3 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[546]  arXiv:2405.12122 [pdf, other]
Title: An Active Learning Framework with a Class Balancing Strategy for Time Series Classification
Authors: Shemonto Das
Comments: Master's thesis accepted by Memorial University of Newfoundland. Chapter 3 published in the Journal of Frontiers in Robotics and AI. Chapter 4 published in the IEEE Systems Conference 2024
Subjects: Machine Learning (cs.LG)
[547]  arXiv:2405.12096 [pdf, other]
Title: PATE: Proximity-Aware Time series anomaly Evaluation
Comments: Accepted by ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2024), Research Track. (Preprint version)
Subjects: Machine Learning (cs.LG)
[548]  arXiv:2405.12094 [pdf, other]
Title: Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Comments: 20 pages, 8 figures
Subjects: Machine Learning (cs.LG)
[549]  arXiv:2405.12087 [pdf, other]
Title: Channel Balance Interpolation in the Lightning Network via Machine Learning
Subjects: Machine Learning (cs.LG)
[550]  arXiv:2405.12046 [pdf, other]
Title: Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach
Comments: Submitted to IEEE journals for possible publication
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Information Theory (cs.IT); Signal Processing (eess.SP)
[551]  arXiv:2405.12038 [pdf, other]
Title: Adaptive Extraction Network for Multivariate Long Sequence Time-Series Forecasting
Subjects: Machine Learning (cs.LG); Information Retrieval (cs.IR)
[552]  arXiv:2405.12001 [pdf, other]
Title: Scrutinize What We Ignore: Reining Task Representation Shift In Context-Based Offline Meta Reinforcement Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[553]  arXiv:2405.11982 [pdf, other]
Title: Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[554]  arXiv:2405.11968 [pdf, other]
Title: Conditional Shift-Robust Conformal Prediction for Graph Neural Network
Authors: S. Akansha
Comments: 11 pages, 4 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[555]  arXiv:2405.11958 [pdf, other]
Title: Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis
Subjects: Machine Learning (cs.LG); Human-Computer Interaction (cs.HC)
[556]  arXiv:2405.11951 [pdf, other]
Title: Distinguished In Uniform: Self Attention Vs. Virtual Nodes
Journal-ref: The Twelfth International Conference on Learning Representations (2024)
Subjects: Machine Learning (cs.LG)
[557]  arXiv:2405.11930 [pdf, other]
Title: Data Contamination Calibration for Black-box LLMs
Subjects: Machine Learning (cs.LG)
[558]  arXiv:2405.11919 [pdf, other]
Title: On Efficient and Statistical Quality Estimation for Data Annotation
Comments: Accepted to ACL 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[559]  arXiv:2405.11916 [pdf, ps, other]
Title: Information Leakage from Embedding in Large Language Models
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[560]  arXiv:2405.11907 [pdf, other]
Title: Ensemble and Mixture-of-Experts DeepONets For Operator Learning
Subjects: Machine Learning (cs.LG)
[561]  arXiv:2405.11895 [pdf, other]
Title: Sparse Attention-driven Quality Prediction for Production Process Optimization in Digital Twins
Subjects: Machine Learning (cs.LG); Systems and Control (eess.SY)
[562]  arXiv:2405.11884 [pdf, other]
Title: Vertical Federated Learning Hybrid Local Pre-training
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
[563]  arXiv:2405.11881 [pdf, other]
Title: Out-of-Distribution Detection with a Single Unconditional Diffusion Model
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
[564]  arXiv:2405.11880 [pdf, other]
Title: Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
[565]  arXiv:2405.11868 [pdf, other]
Title: Towards Graph Contrastive Learning: A Survey and Beyond
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Information Retrieval (cs.IR); Social and Information Networks (cs.SI)
[566]  arXiv:2405.11829 [pdf, other]
Title: Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[567]  arXiv:2405.11828 [pdf, other]
Title: Federated Learning with Incomplete Sensing Modalities
Subjects: Machine Learning (cs.LG)
[568]  arXiv:2405.11821 [pdf, ps, other]
Title: A Three-Phase Analysis of Synergistic Effects During Co-pyrolysis of Algae and Wood for Biochar Yield Using Machine Learning
Comments: 6 pages
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[569]  arXiv:2405.11811 [pdf, other]
Title: FedCAda: Adaptive Client-Side Optimization for Accelerated and Stable Federated Learning
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
[570]  arXiv:2405.11801 [pdf, other]
Title: LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
Comments: Accepted by ICML24, 26 pages
Subjects: Machine Learning (cs.LG)
[571]  arXiv:2405.11788 [pdf, other]
Title: TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models
Comments: Our codebase is made public at this https URL with documentation available at this https URL
Subjects: Machine Learning (cs.LG)
[572]  arXiv:2405.11784 [pdf, other]
Title: Reward-Punishment Reinforcement Learning with Maximum Entropy
Comments: IJCNN2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
[573]  arXiv:2405.11783 [pdf, ps, other]
Title: Inverse Design of Metal-Organic Frameworks Using Quantum Natural Language Processing
Comments: 45 pages, 7 figures, 6 supplementary figures, 1 table, 1 supplementary table
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Quantum Physics (quant-ph)
[574]  arXiv:2405.11778 [pdf, other]
Title: Efficient Multi-agent Reinforcement Learning by Planning
Comments: ICLR2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
[575]  arXiv:2405.11762 [pdf, ps, other]
Title: Uncertainty of interpretability in Landslide Susceptibility Mapping: A Comparative Analysis of Statistical, Machine Learning, and Deep Learning Models
Authors: Cheng Chen, Lei Fan
Subjects: Machine Learning (cs.LG)
[576]  arXiv:2405.11758 [pdf, other]
Title: Fed-Credit: Robust Federated Learning with Credibility Management
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[577]  arXiv:2405.11756 [pdf, other]
Title: Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
Authors: Kai Gan, Tong Wei
Comments: Accepted to ICML 2024
Subjects: Machine Learning (cs.LG)
[578]  arXiv:2405.11743 [pdf, other]
Title: A General Theory for Compositional Generalization
Subjects: Machine Learning (cs.LG)
[579]  arXiv:2405.11740 [pdf, other]
Title: Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[580]  arXiv:2405.11739 [pdf, ps, other]
Title: Contactless Polysomnography: What Radio Waves Tell Us about Sleep
Comments: The first two authors contributed equally to this work
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
[581]  arXiv:2405.11730 [pdf, ps, other]
Title: Degree of Irrationality: Sentiment and Implied Volatility Surface
Authors: Jiahao Weng, Yan Xie
Comments: 21 pages, 8 figures
Subjects: Machine Learning (cs.LG); General Finance (q-fin.GN)
[582]  arXiv:2405.11727 [pdf, other]
Title: Highway Graph to Accelerate Reinforcement Learning
Comments: 28 pages, 17 figures, 3 tables, TMLR
Subjects: Machine Learning (cs.LG)
[583]  arXiv:2405.11718 [pdf, other]
Title: Feasibility Consistent Representation Learning for Safe Reinforcement Learning
Comments: ICML 2024
Subjects: Machine Learning (cs.LG)
[584]  arXiv:2405.11708 [pdf, other]
Title: Adaptive Batch Normalization Networks for Adversarial Robustness
Comments: Accepted at IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS) 2024
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[585]  arXiv:2405.11704 [pdf, ps, other]
Title: Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[586]  arXiv:2405.11703 [pdf, other]
Title: QComp: A QSAR-Based Data Completion Framework for Drug Discovery
Subjects: Machine Learning (cs.LG)
[587]  arXiv:2405.11696 [pdf, other]
Title: Approximation and Gradient Descent Training with Neural Networks
Authors: G. Welper
Subjects: Machine Learning (cs.LG)
[588]  arXiv:2405.11684 [pdf, other]
Title: Learning Regularities from Data using Spiking Functions: A Theory
Subjects: Machine Learning (cs.LG); Information Theory (cs.IT)
[589]  arXiv:2405.11683 [pdf, other]
Title: Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation
Comments: 23 pages, 2 figures, ICML
Subjects: Machine Learning (cs.LG)
[590]  arXiv:2405.11672 [pdf, ps, other]
Title: Interpretable Machine Learning Enhances Disease Prognosis: Applications on COVID-19 and Onward
Authors: Jinzhi Shen, Ke Ma
Subjects: Machine Learning (cs.LG)
[591]  arXiv:2405.11669 [pdf, other]
Title: Do No Harm: A Counterfactual Approach to Safe Reinforcement Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[592]  arXiv:2405.11667 [pdf, other]
Title: The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Optimization and Control (math.OC); Machine Learning (stat.ML)
[593]  arXiv:2405.11657 [pdf, other]
Title: On the Expressivity of Recurrent Neural Cascades with Identity
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Formal Languages and Automata Theory (cs.FL); Logic in Computer Science (cs.LO); Neural and Evolutionary Computing (cs.NE)
[594]  arXiv:2405.11651 [pdf, other]
Title: Movie Revenue Prediction using Machine Learning Models
Comments: for associated code base, see this https URL
Subjects: Machine Learning (cs.LG)
[595]  arXiv:2405.11633 [pdf, other]
Title: Geometry-Aware Instrumental Variable Regression
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[596]  arXiv:2405.11619 [pdf, ps, other]
Title: Novel Interpretable and Robust Web-based AI Platform for Phishing Email Detection
Comments: 19 pages, 7 figures, dataset link: this https URL
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[597]  arXiv:2405.11605 [pdf, other]
Title: Switched Flow Matching: Eliminating Singularities via Switching ODEs
Authors: Qunxi Zhu, Wei Lin
Comments: Accepted in ICML 2024
Subjects: Machine Learning (cs.LG)
[598]  arXiv:2405.11601 [pdf, ps, other]
Title: How to integrate cloud service, data analytic and machine learning technique to reduce cyber risks associated with the modern cloud based infrastructure
Authors: Upakar Bhatta
Comments: 15 pages with six figures
Subjects: Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE)
[599]  arXiv:2405.11590 [pdf, other]
Title: Global Convergence of Decentralized Retraction-Free Optimization on the Stiefel Manifold
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC)
[600]  arXiv:2405.11573 [pdf, other]
Title: Quantile Activation: departing from single point estimation for better generalization across distortions
Subjects: Machine Learning (cs.LG)
[601]  arXiv:2405.11566 [pdf, other]
Title: Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models
Subjects: Machine Learning (cs.LG)
[602]  arXiv:2405.11548 [pdf, other]
Title: Adaptive Online Experimental Design for Causal Discovery
Comments: To appear in Proceedings of ICML 24
Subjects: Machine Learning (cs.LG); Applications (stat.AP)
[603]  arXiv:2405.11542 [pdf, other]
Title: From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
Subjects: Machine Learning (cs.LG); Physics Education (physics.ed-ph)
[604]  arXiv:2405.11533 [pdf, other]
Title: Hierarchical Selective Classification
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[605]  arXiv:2405.11530 [pdf, other]
Title: Learning More Generalized Experts by Merging Experts in Mixture-of-Experts
Authors: Sejik Park
Comments: 12 pages, 3 figures
Subjects: Machine Learning (cs.LG)
[606]  arXiv:2405.11525 [pdf, other]
Title: Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors
Comments: Paper Accepted at ICML 2024, 23 pages
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[607]  arXiv:2405.11500 [pdf, other]
Title: Interpreting a Semantic Segmentation Model for Coastline Detection
Journal-ref: 2023 Photonics & Electromagnetics Research Symposium (PIERS)
Subjects: Machine Learning (cs.LG)
[608]  arXiv:2405.11470 [pdf, other]
Title: VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting
Comments: 16 pages
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[609]  arXiv:2405.11454 [pdf, ps, other]
Title: Comparisons Are All You Need for Optimizing Smooth Functions
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Optimization and Control (math.OC)
[610]  arXiv:2405.11449 [pdf, other]
Title: NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba
Subjects: Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
[611]  arXiv:2405.11432 [pdf, other]
Title: On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks
Subjects: Machine Learning (cs.LG); Systems and Control (eess.SY)
[612]  arXiv:2405.11431 [pdf, other]
Title: Review of deep learning models for crypto price prediction: implementation and evaluation
Subjects: Machine Learning (cs.LG); Statistical Finance (q-fin.ST); Machine Learning (stat.ML)
[613]  arXiv:2405.11417 [pdf, other]
Title: Budgeted Recommendation with Delayed Feedback
Subjects: Machine Learning (cs.LG)
[614]  arXiv:2405.11416 [pdf, other]
Title: Discrete-state Continuous-time Diffusion for Graph Generation
Subjects: Machine Learning (cs.LG)
[615]  arXiv:2405.11397 [pdf, other]
Title: Preparing for Black Swans: The Antifragility Imperative for Machine Learning
Authors: Ming Jin
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
[616]  arXiv:2405.11389 [pdf, other]
Title: Adjacent Leader Decentralized Stochastic Gradient Descent
Comments: 9 pages of main paper, and 12 pages of appendix
Subjects: Machine Learning (cs.LG)
[617]  arXiv:2405.11383 [pdf, ps, other]
Title: Investigating KAN-Based Physics-Informed Neural Networks for EMI/EMC Simulations
Comments: 8 pages
Subjects: Machine Learning (cs.LG)
[618]  arXiv:2405.11372 [pdf, other]
Title: ReModels: Quantile Regression Averaging models
Subjects: Machine Learning (cs.LG)
[619]  arXiv:2405.11349 [pdf, other]
Title: Unlock the Power of Algorithm Features: A Generalization Analysis for Algorithm Selection
Subjects: Machine Learning (cs.LG)
[620]  arXiv:2405.11344 [pdf, ps, other]
Title: Improved Content Understanding With Effective Use of Multi-task Contrastive Learning
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[621]  arXiv:2405.11333 [pdf, other]
Title: GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing
Comments: Accepted by KDD 2024 (Research track)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[622]  arXiv:2405.11331 [pdf, other]
Title: Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks
Comments: 13 pages, 5 figures. Submission for possible publication
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
[623]  arXiv:2405.11326 [pdf, other]
Title: On the Trajectory Regularity of ODE-based Diffusion Sampling
Comments: ICML 2024, 30 pages
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[624]  arXiv:2405.11320 [pdf, other]
Title: Sampling Strategies for Mitigating Bias in Face Synthesis Methods
Comments: Accepted to the BIAS 2023 ECML-PKDD Workshop
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
[625]  arXiv:2405.11318 [pdf, other]
Title: Smooth Kolmogorov Arnold networks enabling structural knowledge representation
Subjects: Machine Learning (cs.LG); Disordered Systems and Neural Networks (cond-mat.dis-nn); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
[626]  arXiv:2405.11311 [pdf, ps, other]
Title: A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis
Subjects: Machine Learning (cs.LG); Emerging Technologies (cs.ET)
[627]  arXiv:2405.11280 [pdf, other]
Title: Joint Analysis of Single-Cell Data across Cohorts with Missing Modalities
Comments: 10 pages, 7 figures, 5 tables
Subjects: Machine Learning (cs.LG)
[628]  arXiv:2405.11275 [pdf, other]
Title: Predicting and Explaining Hearing Aid Usage Using Encoder-Decoder with Attention Mechanism and SHAP
Journal-ref: In 16th SITIS, pp. 308-315. IEEE, 2022
Subjects: Machine Learning (cs.LG)
[629]  arXiv:2405.11238 [pdf, other]
Title: SimAD: A Simple Dissimilarity-based Approach for Time Series Anomaly Detection
Comments: 18 pages, 12 figures,7 tables, Under review
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[630]  arXiv:2405.11230 [pdf, other]
Title: OTLP: Output Thresholding Using Mixed Integer Linear Programming
Comments: 15 pages, 8 figures
Subjects: Machine Learning (cs.LG)
[631]  arXiv:2405.11226 [pdf, ps, other]
Title: The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback
Subjects: Machine Learning (cs.LG)
[632]  arXiv:2405.11206 [pdf, other]
Title: Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
[633]  arXiv:2405.11204 [pdf, other]
Title: Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Dueling
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[634]  arXiv:2405.11195 [pdf, other]
Title: Trustworthy Actionable Perturbations
Comments: Accepted at the 41st International Conference on Machine Learning (ICML) 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Information Theory (cs.IT)
[635]  arXiv:2405.11188 [pdf, other]
Title: Wind Power Prediction across Different Locations using Deep Domain Adaptive Learning
Subjects: Machine Learning (cs.LG)
[636]  arXiv:2405.11171 [pdf, other]
Title: Graph Feedback Bandits with Similar Arms
Authors: Han Qi, Guo Fei, Li Zhu
Subjects: Machine Learning (cs.LG)
[637]  arXiv:2405.11157 [pdf, other]
Title: Towards Modular LLMs by Building and Reusing a Library of LoRAs
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL)
[638]  arXiv:2405.11124 [pdf, other]
Title: AdaWaveNet: Adaptive Wavelet Network for Time Series Analysis
Subjects: Machine Learning (cs.LG)
[639]  arXiv:2405.11095 [pdf, other]
Title: Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance
Comments: 20 pages
Subjects: Machine Learning (cs.LG); Numerical Analysis (math.NA); Optimization and Control (math.OC)
[640]  arXiv:2405.11059 [pdf, other]
Title: Frugal Algorithm Selection
Comments: 7 pages + references + appendix
Subjects: Machine Learning (cs.LG)
[641]  arXiv:2405.11034 [pdf, other]
Title: Safety in Graph Machine Learning: Threats and Safeguards
Comments: 20 pages
Subjects: Machine Learning (cs.LG)
[642]  arXiv:2405.11029 [pdf, other]
Title: Generative Artificial Intelligence: A Systematic Review and Applications
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
[643]  arXiv:2405.11024 [pdf, other]
Title: GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection
Comments: Accepted by KDD 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[644]  arXiv:2405.11013 [pdf, other]
Title: ARDDQN: Attention Recurrent Double Deep Q-Network for UAV Coverage Path Planning and Data Harvesting
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[645]  arXiv:2405.11008 [pdf, ps, other]
Title: A Systematic Review and Meta-Analysis on Sleep Stage Classification and Sleep Disorder Detection Using Artificial Intelligence
Comments: 40 pages, 11 Figures, 8 Tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[646]  arXiv:2405.11007 [pdf, other]
Title: Generative modeling of Sparse Approximate Inverse Preconditioners
Comments: 15 pages, 8 figures, International conference on Computational Science
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[647]  arXiv:2405.11002 [pdf, other]
Title: Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detection
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
[648]  arXiv:2405.10999 [pdf, other]
Title: Large Language Models for Tuning Evolution Strategies
Authors: Oliver Kramer
Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Neural and Evolutionary Computing (cs.NE)
[649]  arXiv:2405.10995 [pdf, other]
Title: Physics-incorporated Graph Neural Network for Multivariate Time Series Imputation
Comments: 18 pages, 7 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[650]  arXiv:2405.10992 [pdf, other]
Title: Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System
Comments: ACL 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[651]  arXiv:2405.10991 [pdf, other]
Title: Relative Counterfactual Contrastive Learning for Mitigating Pretrained Stance Bias in Stance Detection
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Methodology (stat.ME)
[652]  arXiv:2405.10989 [pdf, other]
Title: Learnable Privacy Neurons Localization in Language Models
Comments: ACL 2024 main conference
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR)
[653]  arXiv:2405.10988 [pdf, other]
Title: Flow Score Distillation for Diverse Text-to-3D Generation
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[654]  arXiv:2405.10987 [pdf, other]
Title: Manifold-based Incomplete Multi-view Clustering via Bi-Consistency Guidance
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[655]  arXiv:2405.10976 [pdf, other]
Title: On Constructing Algorithm Portfolios in Algorithm Selection for Computationally Expensive Black-box Optimization in the Fixed-budget Setting
Comments: Accepted for GECCO 2024 Workshop Industrial Applications of Metaheuristics
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
[656]  arXiv:2405.10970 [pdf, other]
Title: Untargeted Adversarial Attack on Knowledge Graph Embeddings
Comments: Accepted by SIGIR 2024
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
[ total of 931 entries: 1-656 | 657-931 ]
[ showing 656 entries per page: fewer | more | all ]

Disable MathJax (What is MathJax?)

Links to: arXiv, form interface, find, cs, new, 2405, contact, help  (Access key information)