Machine Learning

Authors and titles for cs.LG in Feb 2021, skipping first 25

[26]  arXiv:2102.00428 [pdf, other]

Title: PyTorch-Hebbian: facilitating local learning in a deep learning framework

Authors: Jules Talloen, Joni Dambre, Alexander Vandesompele

Comments: Presented as a poster at the NeurIPS 2020 Beyond Backpropagation workshop

Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

[27]  arXiv:2102.00431 [pdf, other]

Title: Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting

Authors: Longyuan Li, Jihai Zhang, Junchi Yan, Yaohui Jin, Yunhao Zhang, Yanjie Duan, Guangjian Tian

Comments: Accepted by AAAI 2021 conference

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)

[28]  arXiv:2102.00434 [pdf, ps, other]

Title: The Connection Between Approximation, Depth Separation and Learnability in Neural Networks

Authors: Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir

Comments: COLT 2021 camera ready version

Subjects: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Machine Learning (stat.ML)

[29]  arXiv:2102.00451 [pdf, ps, other]

Title: Exponential Savings in Agnostic Active Learning through Abstention

Authors: Nikita Puchkin, Nikita Zhivotovskiy

Comments: 31 pages, IEEE Transactions on Information Theory

Subjects: Machine Learning (cs.LG); Information Theory (cs.IT); Statistics Theory (math.ST)

[30]  arXiv:2102.00457 [pdf, other]

Title: MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification

Authors: Chang Wei Tan, Angus Dempster, Christoph Bergmeir, Geoffrey I. Webb

Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

[31]  arXiv:2102.00479 [pdf, other]

Title: Fast Rates for the Regret of Offline Reinforcement Learning

Authors: Yichun Hu, Nathan Kallus, Masatoshi Uehara

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC); Machine Learning (stat.ML)

[32]  arXiv:2102.00485 [pdf, other]

Title: Exploring the Geometry and Topology of Neural Network Loss Landscapes

Authors: Stefan Horoi, Jessie Huang, Bastian Rieck, Guillaume Lajoie, Guy Wolf, Smita Krishnaswamy

Comments: Accepted at the 20th Symposium on Intelligent Data Analysis (IDA) 2022

Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

[33]  arXiv:2102.00490 [pdf, ps, other]

Title: Online Markov Decision Processes with Aggregate Bandit Feedback

Authors: Alon Cohen, Haim Kaplan, Tomer Koren, Yishay Mansour

Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

[34]  arXiv:2102.00500 [pdf, other]

Title: A Multiscale Environment for Learning by Diffusion

Authors: James M. Murphy, Sam L. Polk

Comments: 35 pages, 10 figures

Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Probability (math.PR); Machine Learning (stat.ML)

[35]  arXiv:2102.00504 [pdf, other]

Title: Exact Recovery of Clusters in Finite Metric Spaces Using Oracle Queries

Authors: Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice

Comments: Accepted for presentation at the Conference on Learning Theory (COLT) 2021

Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

[36]  arXiv:2102.00523 [pdf, ps, other]

Title: Co-Seg: An Image Segmentation Framework Against Label Corruption

Authors: Ziyi Huang, Haofeng Zhang, Andrew Laine, Elsa Angelini, Christine Hendon, Yu Gan

Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

[37]  arXiv:2102.00527 [pdf, other]

Title: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training

Authors: Geoffrey X. Yu, Yubo Gao, Pavel Golikov, Gennady Pekhimenko

Comments: 19 pages, 7 figures. Appears in the Proceedings of the 2021 USENIX Annual Technical Conference (USENIX ATC '21). Code available at this https URL

Subjects: Machine Learning (cs.LG); Performance (cs.PF)

[38]  arXiv:2102.00533 [pdf, other]

Title: Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional

Authors: Xi Yu, Shujian Yu, Jose C. Principe

Comments: Accepted at ICASSP-21. Code available at this https URL Extended version of the suppelementary material in "Measuring the Dependence with Matrix-based Entropy Functional", AAAI-21, arXiv:2101.10160

Subjects: Machine Learning (cs.LG); Information Theory (cs.IT)

[39]  arXiv:2102.00534 [pdf, ps, other]

Title: Generative and Discriminative Deep Belief Network Classifiers: Comparisons Under an Approximate Computing Framework

Authors: Siqiao Ruan, Ian Colbert, Ken Kreutz-Delgado, Srinjoy Das

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)

[40]  arXiv:2102.00538 [pdf, other]

Title: CODE-AE: A Coherent De-confounding Autoencoder for Predicting Patient-Specific Drug Response From Cell Line Transcriptomics

Authors: Di He, Lei Xie

Subjects: Machine Learning (cs.LG); Genomics (q-bio.GN)

[41]  arXiv:2102.00546 [pdf, other]

Title: GraphEBM: Molecular Graph Generation with Energy-Based Models

Authors: Meng Liu, Keqiang Yan, Bora Oztekin, Shuiwang Ji

Comments: Accepted by Energy-Based Models Workshop ICLR 2021

Subjects: Machine Learning (cs.LG)

[42]  arXiv:2102.00554 [pdf, other]

Title: Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks

Authors: Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, Alexandra Peste

Comments: 90 pages, 26 figures

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR); Computer Vision and Pattern Recognition (cs.CV); Neural and Evolutionary Computing (cs.NE)

[43]  arXiv:2102.00628 [pdf, ps, other]

Title: Spatiotemporal Ground Reaction Force Analysis using Convolutional Neural Networks to Analyze Parkinsonian Gait

Authors: Musthaq Ahamed, P.D.S.H. Gunawardane, Nimali T. Medagedara

Subjects: Machine Learning (cs.LG); Signal Processing (eess.SP)

[44]  arXiv:2102.00637 [pdf, ps, other]

Title: Computing the Hazard Ratios Associated with Explanatory Variables Using Machine Learning Models of Survival Data

Authors: Sameer Sundrani, James Lu

Comments: 27 pages, 5 figures, 1 table

Journal-ref: JCO Clinical Cancer Informatics, 2021

Subjects: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)

[45]  arXiv:2102.00650 [pdf, other]

Title: Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective

Authors: Helong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, Qian Zhang

Comments: ICLR 2021

Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

[46]  arXiv:2102.00655 [pdf, other]

Title: Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning

Authors: Syed Zawad, Ahsan Ali, Pin-Yu Chen, Ali Anwar, Yi Zhou, Nathalie Baracaldo, Yuan Tian, Feng Yan

Comments: Accepted in AAAI 2021

Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)

[47]  arXiv:2102.00662 [pdf, other]

Title: Towards Speeding up Adversarial Training in Latent Spaces

Authors: Yaguan Qian, Qiqi Shao, Tengteng Yao, Bin Wang, Shouling Ji, Shaoning Zeng, Zhaoquan Gu, Wassim Swaileh

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

[48]  arXiv:2102.00667 [pdf, ps, other]

Title: Probabilistic Learning Vector Quantization on Manifold of Symmetric Positive Definite Matrices

Authors: Fengzhen Tang, Haifeng Feng, Peter Tino, Bailu Si, Daxiong Ji

Comments: 15 pages, 7 figures

Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

[49]  arXiv:2102.00678 [pdf, other]

Title: Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification

Authors: Nan Lu, Shida Lei, Gang Niu, Issei Sato, Masashi Sugiyama

Comments: ICML2021 camera-ready version

Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

[50]  arXiv:2102.00696 [pdf, other]

Title: Numerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanisms

Authors: Selim Furkan Tekin, Arda Fazla, Suleyman Serdar Kozat

Comments: - In our journal submission, we removed the integration of the observational data section since it was not used in the experiments. Thus, we also removed the authors from the paper who were responsible for that section. - In the second version, we also performed an experiment on WeatherBench. We compare our results with the Physical Weather Forecasting Models

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)