Machine Learning

Authors and titles for cs.LG in Mar 2023, skipping first 100

[101]  arXiv:2303.01272 [pdf, other]

Title: Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Series

Authors: Sondre Sørbø, Massimiliano Ruocco

Comments: 29 pages, 28 figures and tables

Subjects: Machine Learning (cs.LG)

[102]  arXiv:2303.01289 [pdf, other]

Title: Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

Authors: Rundong Luo, Yifei Wang, Yisen Wang

Comments: ICLR 2023

Subjects: Machine Learning (cs.LG)

[103]  arXiv:2303.01295 [pdf, other]

Title: Iterative Assessment and Improvement of DNN Operational Accuracy

Authors: Antonio Guerriero, Roberto Pietrantuono, Stefano Russo

Comments: Paper accepted at 45th International Conference on Software Engineering (ICSE'23 NIER), May 2023

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

[104]  arXiv:2303.01335 [pdf, other]

Title: First-order ANIL learns linear representations despite misspecified latent dimension

Authors: Oğuz Kaan Yuksel, Etienne Boursier, Nicolas Flammarion

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

[105]  arXiv:2303.01372 [pdf, other]

Title: High-dimensional analysis of double descent for linear regression with random projections

Authors: Francis Bach (SIERRA)

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

[106]  arXiv:2303.01384 [pdf, other]

Title: DAVA: Disentangling Adversarial Variational Autoencoder

Authors: Benjamin Estermann, Roger Wattenhofer

Comments: Published as a conference paper at ICLR 2023

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

[107]  arXiv:2303.01388 [pdf, other]

Title: Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement

Authors: Petr Bobák, Ladislav Čmolík, Martin Čadík

Subjects: Machine Learning (cs.LG)

[108]  arXiv:2303.01391 [pdf, other]

Title: The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting

Authors: Hongyao Tang, Min Zhang, Jianye Hao

Comments: Rudimentary version. Work in progress

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

[109]  arXiv:2303.01412 [pdf, other]

Title: Hyperparameter Tuning and Model Evaluation in Causal Effect Estimation

Authors: Damian Machlanski, Spyridon Samothrakis, Paul Clarke

Comments: 36 pages, 3 figures

Subjects: Machine Learning (cs.LG); Methodology (stat.ME)

[110]  arXiv:2303.01429 [pdf, other]

Title: Optimal transfer protocol by incremental layer defrosting

Authors: Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio

Subjects: Machine Learning (cs.LG)

[111]  arXiv:2303.01433 [pdf, other]

Title: Do Machine Learning Models Learn Statistical Rules Inferred from Data?

Authors: Aaditya Naik, Yinjun Wu, Mayur Naik, Eric Wong

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

[112]  arXiv:2303.01456 [pdf, ps, other]

Title: The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

Authors: Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro

Comments: 42 pages; NeurIPS 2023 camera ready

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

[113]  arXiv:2303.01462 [pdf, ps, other]

Title: Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization

Authors: Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro

Comments: 53 pages

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

[114]  arXiv:2303.01464 [pdf, ps, other]

Title: Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation

Authors: Orin Levy, Alon Cohen, Asaf Cassel, Yishay Mansour

Subjects: Machine Learning (cs.LG)

[115]  arXiv:2303.01469 [pdf, other]

Title: Consistency Models

Authors: Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever

Comments: ICML 2023

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

[116]  arXiv:2303.01475 [pdf, other]

Title: Over-training with Mixup May Hurt Generalization

Authors: Zixuan Liu, Ziqiao Wang, Hongyu Guo, Yongyi Mao

Comments: Accepted to ICLR 2023

Subjects: Machine Learning (cs.LG)

[117]  arXiv:2303.01486 [pdf, other]

Title: Understanding plasticity in neural networks

Authors: Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Avila Pires, Razvan Pascanu, Will Dabney

Comments: Accepted to ICML 2023 (oral presentation)

Subjects: Machine Learning (cs.LG)

[118]  arXiv:2303.01500 [pdf, other]

Title: Dropout Reduces Underfitting

Authors: Zhuang Liu, Zhiqiu Xu, Joseph Jin, Zhiqiang Shen, Trevor Darrell

Comments: ICML 2023

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

[119]  arXiv:2303.01504 [pdf, other]

Title: Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

Authors: Shangxi Wu, Qiuyang He, Fangzhao Wu, Jitao Sang, Yaowei Wang, Changsheng Xu

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

[120]  arXiv:2303.01505 [pdf, other]

Title: Ternary Quantization: A Survey

Authors: Dan Liu, Xue Liu

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

[121]  arXiv:2303.01506 [pdf, other]

Title: Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions

Authors: Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Ziwei Yang, Zheyang Li, Quanshi Zhang

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

[122]  arXiv:2303.01509 [pdf, ps, other]

Title: EPAM: A Predictive Energy Model for Mobile AI

Authors: Anik Mallik, Haoxin Wang, Jiang Xie, Dawei Chen, Kyungtae Han

Comments: Accepted in IEEE International Conference on Communications (ICC); 28 May - 01 June 2023; Rome, Italy; six pages, seven figures, two tables

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

[123]  arXiv:2303.01510 [pdf, other]

Title: INO at Factify 2: Structure Coherence based Multi-Modal Fact Verification

Authors: Yinuo Zhang, Zhulin Tao, Xi Wang, Tongyue Wang

Comments: AAAI-23 DeFactify 2 Workshop (2nd Prize)

Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

[124]  arXiv:2303.01513 [pdf, ps, other]

Title: Safe AI for health and beyond -- Monitoring to transform a health service

Authors: Mahed Abroshan, Michael Burkhart, Oscar Giles, Sam Greenbury, Zoe Kourtzi, Jack Roberts, Mihaela van der Schaar, Jannetta S Steyn, Alan Wilson, May Yong

Comments: 12 pages, 3 figures

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

[125]  arXiv:2303.01538 [pdf, other]

Title: Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks

Authors: Lennart Brocki, Neo Christopher Chung

Journal-ref: ICLR 2023 Workshop on Trustworthy ML; Full Paper in Pattern Recognition Letters

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