ICML

Learning useful representations for radio astronomy "in the wild" with contrastive learning

Inigo Val Slijepcevic, Anna M. M. Scaife, Mike Walmsley, Micah Bowles

Comments Accepted in: Machine Learning for Astrophysics Workshop at the Thirty Ninth International Conference on Machine Learning (ICML 2022); final version

HyperInvariances: Amortizing Invariance Learning

Ruchika Chavhan, Henry Gouk, Jan Stühmer, Timothy Hospedales

Comments ICML 2022, Workshop on Spurious Correlations, Invariance, and Stability

Security Evaluation of Compressible Image Encryption for Privacy-Preserving Image Classification against Ciphertext-only Attacks

Tatsuya Chuman, Hitoshi Kiya

Comments To be appeared in International Conference on Machine Learning and Cybernetics 2022

LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training

Sumanth Gurram, Andy Fang, David Chan, John Canny

Comments Workshop Paper at ICML 2022

Certified Neural Network Watermarks with Randomized Smoothing

Arpit Bansal, Ping-yeh Chiang, Michael Curry, Rajiv Jain, Curtis Wigington, Varun Manjunatha, John P Dickerson, Tom Goldstein

Comments ICML 2022

Journal ref ICML 2022

On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning

Diane Wagner, Fabio Ferreira, Danny Stoll, Robin Tibor Schirrmeister, Samuel Müller, Frank Hutter

Comments Accepted at the ICML 2022 Pre-training Workshop

POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging

Shishir G. Patil, Paras Jain, Prabal Dutta, Ion Stoica, Joseph E. Gonzalez

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

Robust Counterfactual Explanations for Tree-Based Ensembles

Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, Daniele Magazzeni

Comments Accepted at ICML 2022

Feature Selection using e-values

Subhabrata Majumdar, Snigdhansu Chatterjee

Comments accepted in ICML-2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:14753-14773, 2022, https://proceedings.mlr.press/v162/majumdar22a.html

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

Nathan Kallus, Xiaojie Mao, Kaiwen Wang, Zhengyuan Zhou

Comments Short Talk at ICML 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:10598-10632, 2022

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning

Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu

Comments ICML

Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification

Camille Garcin, Maximilien Servajean, Alexis Joly, Joseph Salmon

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:7208-7222, 2022

Regret Minimization with Performative Feedback

Meena Jagadeesan, Tijana Zrnic, Celestine Mendler-Dünner

Comments Appeared at ICML 2022

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

Emanuele Bugliarello, Fangyu Liu, Jonas Pfeiffer, Siva Reddy, Desmond Elliott, Edoardo Maria Ponti, Ivan Vulić

Comments ICML 2022

Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences

Ikko Yamane, Junya Honda, Florian Yger, Masashi Sugiyama

Comments ICML 2021 version with correction to Figure 1 and the appendices

Secure Quantized Training for Deep Learning

Marcel Keller, Ke Sun

Comments 27 pages

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:10912-10938, 2022

Efficient Online ML API Selection for Multi-Label Classification Tasks

Lingjiao Chen, Matei Zaharia, James Zou

Comments Accepted to ICML 2022

Position Prediction as an Effective Pretraining Strategy

Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram, Dan Busbridge, Tatiana Likhomanenko, Joseph Yitan Cheng, Walter Talbott, Chen Huang, Hanlin Goh, Joshua Susskind

Comments Accepted to ICML 2022

CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN

Matan Atad, Vitalii Dmytrenko, Yitong Li, Xinyue Zhang, Matthias Keicher, Jan Kirschke, Bene Wiestler, Ashkan Khakzar, Nassir Navab

Comments Accepted to the ICML 2022 Interpretable Machine Learning in Healthcare (IMLH) Workshop ----- Project website: http://github.com/CAMP-eXplain-AI/Style-CheXplain

Sparse Relational Reasoning with Object-Centric Representations

Alex F. Spies, Alessandra Russo, Murray Shanahan

Comments ICML 2022, DyNN Workshop

pathGCN: Learning General Graph Spatial Operators from Paths

Moshe Eliasof, Eldad Haber, Eran Treister

Comments ICML 2022

Learning to Separate Voices by Spatial Regions

Zhongweiyang Xu, Romit Roy Choudhury

Comments Accepted to ICML 2022. For associated audio samples, see https://uiuc-earable-computing.github.io/binaural

Demystifying the Adversarial Robustness of Random Transformation Defenses

Chawin Sitawarin, Zachary Golan-Strieb, David Wagner

Comments ICML 2022 (short presentation), AAAI 2022 AdvML Workshop (best paper, oral presentation)

Feature Learning in Infinite-Width Neural Networks

Greg Yang, Edward J. Hu

Comments 4th paper in the Tensor Programs series. Appearing in ICML 2021

Accelerated Federated Learning with Decoupled Adaptive Optimization

Jiayin Jin, Jiaxiang Ren, Yang Zhou, Lingjuan Lyu, Ji Liu, Dejing Dou

Journal ref ICML 2022

Provably Adversarially Robust Nearest Prototype Classifiers

Václav Voráček, Matthias Hein

Comments Accepted at ICML 2022

Contrastive Adapters for Foundation Model Group Robustness

Michael Zhang, Christopher Ré

Comments 28 pages, 9 figures. Preprint. Short version accepted to ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability

Reduced Order Model for Chemical Kinetics: A case study with Primordial Chemical Network

Kwok Sun Tang, Matthew Turk

Comments 10 pages, 8 figures, accepted to the ICML 2022 Machine Learning for Astrophysics workshop

Causal Inference Through the Structural Causal Marginal Problem

Luigi Gresele, Julius von Kügelgen, Jonas M. Kübler, Elke Kirschbaum, Bernhard Schölkopf, Dominik Janzing

Comments 32 pages (9 pages main paper + bibliography and appendix), 6 figures

Journal ref International Conference on Machine Learning (ICML 2022), 7793-7824

A Query-Optimal Algorithm for Finding Counterfactuals

Guy Blanc, Caleb Koch, Jane Lange, Li-Yang Tan

Comments 22 pages, ICML 2022