ICML

Robust Semantic Interpretability: Revisiting Concept Activation Vectors

Jacob Pfau, Albert T. Young, Jerome Wei, Maria L. Wei, Michael J. Keiser

Comments ICML WHI 2020

Do We Need Zero Training Loss After Achieving Zero Training Error?

Takashi Ishida, Ikko Yamane, Tomoya Sakai, Gang Niu, Masashi Sugiyama

Comments ICML 2020 camera ready version

Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning

Wonyong Jeong, Jaehong Yoon, Eunho Yang, Sung Ju Hwang

Journal ref International Conference on Learning Representations (ICLR 2021), International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020 (FL-ICML'20)

Learning Human Objectives by Evaluating Hypothetical Behavior

Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, Jan Leike

Comments Published at International Conference on Machine Learning (ICML) 2020

REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data

Xinyun Chen, Wenxiao Wang, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song

Comments ACM Asia Conference on Computer and Communications Security (AsiaCCS), 2021. Early version in ICML 2019 Workshop on Security and Privacy of Machine Learning. The first two authors contribute equally

Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

Wei Deng, Qi Feng, Liyao Gao, Faming Liang, Guang Lin

Comments Accepted by ICML 2020

VAEs in the Presence of Missing Data

Mark Collier, Alfredo Nazabal, Christopher K. I. Williams

Comments Accepted to ICML Workshop on the Art of Learning with Missing Values (Artemiss), 17 July 2020

The role of regularization in classification of high-dimensional noisy Gaussian mixture

Francesca Mignacco, Florent Krzakala, Yue M. Lu, Lenka Zdeborová

Comments 8 pages + appendix, 6 figures

Journal ref International Conference on Machine Learning, ICML 2020

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Dmitrii Beloborodov, A. E. Ulanov, Jakob N. Foerster, Shimon Whiteson, A. I. Lvovsky

Comments Submitted to ICML 2020. 9 pages, 3 pdf figures. V2: fixed acknowledgements

Journal ref Machine Learning: Science and Technology, 2, 025009 (2021)

Hydra: Preserving Ensemble Diversity for Model Distillation

Linh Tran, Bastiaan S. Veeling, Kevin Roth, Jakub Swiatkowski, Joshua V. Dillon, Jasper Snoek, Stephan Mandt, Tim Salimans, Sebastian Nowozin, Rodolphe Jenatton

Comments Accepted to ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning

The Dynamics of Learning: A Random Matrix Approach

Zhenyu Liao, Romain Couillet

Comments 14 pages (with Supplementary Material), 7 figures, ICML 2018

Journal ref Proceedings of the 35th International Conference on Machine Learning (ICML 2018), in PMLR 80:3072-3081

On the Spectrum of Random Features Maps of High Dimensional Data

Zhenyu Liao, Romain Couillet

Comments 13 pages (with Supplementary Material), 10 figure, ICML 2018

Journal ref Proceedings of the 35th International Conference on Machine Learning (ICML 2018), in PMLR 80:3063-3071

CRUDE: Calibrating Regression Uncertainty Distributions Empirically

Eric Zelikman, Christopher Healy, Sharon Zhou, Anand Avati

Comments ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning

A Causal Linear Model to Quantify Edge Flow and Edge Unfairness for UnfairEdge Prioritization and Discrimination Removal

Pavan Ravishankar, Pranshu Malviya, Balaraman Ravindran

Comments Accepted in the Workshop on Law and Machine Learning, ICML 2020; First two authors contributed equally

A Game Theoretic Framework for Model Based Reinforcement Learning

Aravind Rajeswaran, Igor Mordatch, Vikash Kumar

Comments ICML 2020. This version contains expanded discussion, hyperparameter configurations, and ablation studies

Ensemble Hyperspectral Band Selection for Detecting Nitrogen Status in Grape Leaves

Ryan Omidi, Ali Moghimi, Alireza Pourreza, Mohamed El-Hadedy, Anas Salah Eddin

Comments 8 PAGES, ACCEPTED IN 19TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2020), MODIFIED ONE AUTHOR NAME

Selective Dyna-style Planning Under Limited Model Capacity

Zaheer Abbas, Samuel Sokota, Erin J. Talvitie, Martha White

Comments Accepted at ICML 2020

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

Bo Zhao, Xinwei Sun, Yanwei Fu, Yuan Yao, Yizhou Wang

Comments Accepted by the 35th International Conference on Machine Learning

Journal ref International Conference on Machine Learning 2018

Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG

Arshdeep Sekhon, Zhe Wang, Yanjun Qi

Comments 8 pages, 6 figures, version appeared in ICML Workshop 2020 Graph Representation Learning and Beyond (GRL+)

Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models

Michael Oberst, David Sontag

Comments To appear in ICML 2019

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4881-4890, 2019

Interpretable Multi-Modal Hate Speech Detection

Prashanth Vijayaraghavan, Hugo Larochelle, Deb Roy

Comments 5 pages, Accepted at the International Conference on Machine Learning AI for Social Good Workshop, Long Beach, United States, 2019

Journal ref ICML Workshop on AI for Social Good, 2019

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

Gregor N. C. Simm, Robert Pinsler, José Miguel Hernández-Lobato

Journal ref Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

Transformers with Competitive Ensembles of Independent Mechanisms

Alex Lamb, Di He, Anirudh Goyal, Guolin Ke, Chien-Feng Liao, Mirco Ravanelli, Yoshua Bengio

Comments Under Review, ICML 2021

Content-Based Textual File Type Detection at Scale

Francesca Del Bonifro, Maurizio Gabbrielli, Stefano Zacchiroli

Journal ref ICMLC 2021 - Proceedings of International Conference on Machine Learning and Computing 2021

Performative Prediction

Juan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner, Moritz Hardt

Comments published at ICML'20; fixed some typos

Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision Boundary

Shuyue Guan, Murray Loew

Comments 7 pages, 11 figures. Accepted by ICMLA 2020

Journal ref 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020, pp. 101-106

Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks

Blake Bordelon, Abdulkadir Canatar, Cengiz Pehlevan

Comments ICML 2020 Update: Updated section on asymptotics generalization error for power law spectra, finding agreement with Spigler, Geiger, Wyart 2019 arXiv:1905.10843. Added a section on Discrete measures and an MNIST Experiment. Eigenvalue problem can be approximated by Kernel PCA. Typo fixed on 2/25/2021

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:1024-1034, 2020

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates

Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett

Comments ICML 2018

InstaHide: Instance-hiding Schemes for Private Distributed Learning

Yangsibo Huang, Zhao Song, Kai Li, Sanjeev Arora

Comments ICML 2020

Simulation-Based Inference for Global Health Decisions

Christian Schroeder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Rob Zinkov, Puneet Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip Torr, Atılım Güneş Baydin

Journal ref ICML Workshop on Machine Learning for Global Health, Thirty-Seventh International Conference on Machine Learning (ICML 2020)