ICML

Multi-Level Branched Regularization for Federated Learning

Jinkyu Kim, Geeho Kim, Bohyung Han

Comments ICML 2022

DropNet: Reducing Neural Network Complexity via Iterative Pruning

John Tan Chong Min, Mehul Motani

Comments Published at ICML 2020. Code can be found at https://github.com/tanchongmin/DropNet

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:9356-9366, 2020 https://proceedings.mlr.press/v119/tan20a.html

Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes

Gregory Benton, Wesley J. Maddox, Andrew Gordon Wilson

Comments ICML 2022. Code available at https://github.com/g-benton/Volt

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets

Lily H. Zhang, Veronica Tozzo, John M. Higgins, Rajesh Ranganath

Comments Accepted at ICML 2022

Superclass Adversarial Attack

Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

Comments ICML Workshop 2022 on Adversarial Machine Learning Frontiers

Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning

Mayee F. Chen, Daniel Y. Fu, Avanika Narayan, Michael Zhang, Zhao Song, Kayvon Fatahalian, Christopher Ré

Comments ICML 2022 Camera Ready

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation

Wenxiao Wang, Alexander Levine, Soheil Feizi

Comments International Conference on Machine Learning (ICML), 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:22769-22783, 2022

Wide Neural Networks Forget Less Catastrophically

Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar

Comments ICML 2022

FOCUS: Familiar Objects in Common and Uncommon Settings

Priyatham Kattakinda, Soheil Feizi

Comments 23 pages, 14 figures, 4 tables. Accepted to ICML 2022

Rethinking Multidimensional Discriminator Output for Generative Adversarial Networks

Mengyu Dai, Haibin Hang, Anuj Srivastava

Comments Frontiers in Adversarial Machine Learning ICML 2022

Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

Shuo Yang, Erkun Yang, Bo Han, Yang Liu, Min Xu, Gang Niu, Tongliang Liu

Comments ICML 22 camera ready

Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness

Namuk Park, Songkuk Kim

Comments ICML 2022

DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck

Jiameng Fan, Wenchao Li

Comments Accepted at ICML 2022, 29 pages

Fixing Inventory Inaccuracies At Scale

Vivek F. Farias, Andrew A. Li, Tianyi Peng

Comments The preliminary version titled "Near-Optimal Entrywise Anomaly Detection for Low-Rank Matrices with Sub-Exponential Noise" appeared at Proceedings of the 38th International Conference on Machine Learning (ICML 2021)

Policy Optimization with Sparse Global Contrastive Explanations

Jiayu Yao, Sonali Parbhoo, Weiwei Pan, Finale Doshi-Velez

Comments Accepted at IMLH Workshop, ICML 2022

Towards understanding how momentum improves generalization in deep learning

Samy Jelassi, Yuanzhi Li

Comments Accepted at ICML 2022

Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces

Yinglun Zhu, Paul Mineiro

Comments To appear at ICML 2022

Learning Bellman Complete Representations for Offline Policy Evaluation

Jonathan D. Chang, Kaiwen Wang, Nathan Kallus, Wen Sun

Comments Accepted for Long Talk at ICML 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:2938-2971, 2022

Contextual Bandits with Large Action Spaces: Made Practical

Yinglun Zhu, Dylan J. Foster, John Langford, Paul Mineiro

Comments To appear at ICML 2022

dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation

Sofiane Mahiou, Kai Xu, Georgi Ganev

Comments Accepted at the Theory and Practice of Differential Privacy (TPDP) 2022, part of ICML 2022

Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction

Charles Lu, Syed Rakin Ahmed, Praveer Singh, Jayashree Kalpathy-Cramer

Comments Principles of Distribution Shift (PODS) Workshop at ICML 2022

Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization

Liam Peet-Pare, Nidhi Hegde, Alona Fyshe

Comments From a submission to Responsible Decision Making in Dynamics Environments Workshop at ICML 2022

Human-AI Collaboration in Decision-Making: Beyond Learning to Defer

Diogo Leitão, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Comments ICML 2022 Workshop on Human-Machine Collaboration and Teaming

Online Algorithms with Multiple Predictions

Keerti Anand, Rong Ge, Amit Kumar, Debmalya Panigrahi

Comments ICML 2022

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses

Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, Taylan Cemgil

Comments ICML'22

Online Decision Transformer

Qinqing Zheng, Amy Zhang, Aditya Grover

Comments Accepted to ICML 2022 (Long Oral Presentation)

Surrogate Likelihoods for Variational Annealed Importance Sampling

Martin Jankowiak, Du Phan

Comments 21 pages; to appear at ICML 2022

How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective

Akhilan Boopathy, Ila Fiete

Comments Published at ICML 2022, 28 pages, 9 figures

Scalable Bayesian Inference for Detection and Deblending in Astronomical Images

Derek Hansen, Ismael Mendoza, Runjing Liu, Ziteng Pang, Zhe Zhao, Camille Avestruz, Jeffrey Regier

Comments Accepted to the ICML 2022 Workshop on Machine Learning for Astrophysics. 5 pages, 2 figures

Neural Posterior Estimation with Differentiable Simulators

Justine Zeghal, François Lanusse, Alexandre Boucaud, Benjamin Remy, Eric Aubourg

Comments Accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics