ICML

Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality

Changxiao Cai, H. Vincent Poor, Yuxin Chen

Comments Accepted in part to ICML 2020

Journal ref IEEE Transactions on Information Theory, vol. 69, no. 1, pp. 407-452, Jan. 2023

Reducing Exploitability with Population Based Training

Pavel Czempin, Adam Gleave

Comments Presented at New Frontiers in Adversarial Machine Learning Workshop, ICML 2022

Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization

Jaehong Yoon, Geon Park, Wonyong Jeong, Sung Ju Hwang

Comments ICML 2022

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

Junlin Wu, Yevgeniy Vorobeychik

Comments ICML 2022

Goal Misgeneralization in Deep Reinforcement Learning

Lauro Langosco, Jack Koch, Lee Sharkey, Jacob Pfau, Laurent Orseau, David Krueger

Comments Published in ICML 2022. 9 Pages

Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?

Luca Pasqualini, Gianluca Amato, Marco Fantozzi, Rosa Gini, Alessandro Marchetti, Carlo Metta, Francesco Morandin, Maurizio Parton

Comments Published at 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA). This version (v2) is a major revision and superseeds version v1

Moreau-Yosida $f$-divergences

Dávid Terjék

Comments ICML 2021 camera ready with appendix, 38 pages, 15 figures

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10214-10224, 2021

Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing

Izzeddin Teeti, Valentina Musat, Salman Khan, Alexander Rast, Fabio Cuzzolin, Andrew Bradley

Comments ICML 2022

Secure Distributed Training at Scale

Eduard Gorbunov, Alexander Borzunov, Michael Diskin, Max Ryabinin

Comments Accepted to International Conference on Machine Learning (ICML 2022). 61 pages, 10 figures. The version 4 fixes inaccuracies in the proofs of Lemmas E.2 and E.4. Code: https://github.com/yandex-research/btard

Eliminating Meta Optimization Through Self-Referential Meta Learning

Louis Kirsch, Jürgen Schmidhuber

Comments The first version appeared at ICML 2022, DARL Workshop

On Implicit Bias in Overparameterized Bilevel Optimization

Paul Vicol, Jonathan Lorraine, Fabian Pedregosa, David Duvenaud, Roger Grosse

Comments ICML 2022

Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games

Siqi Liu, Marc Lanctot, Luke Marris, Nicolas Heess

Journal ref Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

Convergence of Invariant Graph Networks

Chen Cai, Yusu Wang

Comments 29 pages, 11 figures

Journal ref ICML 2022

Planning with Diffusion for Flexible Behavior Synthesis

Michael Janner, Yilun Du, Joshua B. Tenenbaum, Sergey Levine

Comments ICML 2022 (long talk). Project page and code at https://diffusion-planning.github.io/

Deduplicating Training Data Mitigates Privacy Risks in Language Models

Nikhil Kandpal, Eric Wallace, Colin Raffel

Comments ICML 2022 Camera Ready Version

FriendlyCore: Practical Differentially Private Aggregation

Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer

Comments Published in ICML 2022

Analyzing the Traffic of MANETs using Graph Neural Networks

Taha Tekdogan

Comments International Conference on Machine Learning & Applied Network Technologies (ICMLANT) 2022

Learning with linear mixed model for group recommendation systems

Baode Gao, Guangpeng Zhan, Hanzhang Wang, Yiming Wang, Shengxin Zhu

Comments 5 pages, 9 figures, published

Journal ref In Proceedings of the 2019 11th International Conference on Machine Learning and Computing (pp. 81-85) (2019, February)

Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving

Jonathan Francis, Bingqing Chen, Weiran Yao, Eric Nyberg, Jean Oh

Comments Accepted: 1st Workshop on Safe Learning for Autonomous Driving, at the International Conference on Machine Learning (ICML 2022); Best Paper Award

Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology

Valentin Hofmann, Janet B. Pierrehumbert, Hinrich Schütze

Comments ICML 2022

Galaxies on graph neural networks: towards robust synthetic galaxy catalogs with deep generative models

Yesukhei Jagvaral, Francois Lanusse, Sukhdeep Singh, Rachel Mandelbaum, Siamak Ravanbakhsh, Duncan Campbell

Comments Accepted as extended abstract at ICML 2022 Workshop on Machine Learning for Astrophysics. Condensed version of arXiv:2204.07077

TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data

Beichen Zhang, Frank Schilder, Kelly Helm Smith, Michael J. Hayes, Sherri Harms, Tsegaye Tadesse

Comments 5 pages (+3 in appendix), 5 figures in appendix, 2 tables (+1 in appendix), ICML Workshop on Tackling Climate Change with Machine Learning Workshop, 2021

Making Linear MDPs Practical via Contrastive Representation Learning

Tianjun Zhang, Tongzheng Ren, Mengjiao Yang, Joseph E. Gonzalez, Dale Schuurmans, Bo Dai

Comments ICML 2022. The first two authors contribute equally

Adapting the Linearised Laplace Model Evidence for Modern Deep Learning

Javier Antorán, David Janz, James Urquhart Allingham, Erik Daxberger, Riccardo Barbano, Eric Nalisnick, José Miguel Hernández-Lobato

Comments Paper appearing at ICML 2022

Out-of-Distribution Detection with Deep Nearest Neighbors

Yiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan Li

Comments 15 pages, 4 figures, accepted in ICML 2022

Stochastic Rising Bandits

Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli

Comments Corrected definition of "cumulative increment" (Equation 2) and efficient update (Appendix D)

Journal ref International Conference on Machine Learning (ICML). 2022

Stable Conformal Prediction Sets

Eugene Ndiaye

Comments Update to ICML version

Journal ref Proceedings of the 39-th International Conference on Machine Learning, 2022

Efficient PAC Learning from the Crowd with Pairwise Comparisons

Shiwei Zeng, Jie Shen

Comments v3 proposes a simpler Filter algorithm, hence simpler analysis. v4 added more related works and was accepted to ICML 2022

Spread Divergence

Mingtian Zhang, Peter Hayes, Tom Bird, Raza Habib, David Barber

Journal ref Volume 119: International Conference on Machine Learning, 13-18 July 2020, Virtual

PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks

Enrico Meloni, Lapo Faggi, Simone Marullo, Alessandro Betti, Matteo Tiezzi, Marco Gori, Stefano Melacci

Comments 9 pages, accepted at International Conference on Machine Learning and Applications