ICML

NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation

Tong Zhou, Yukui Luo, Shaolei Ren, Xiaolin Xu

Comments To appear at ICML 2023

Online Platt Scaling with Calibeating

Chirag Gupta, Aaditya Ramdas

Comments ICML 2023; 24 pages and 16 figures

Change is Hard: A Closer Look at Subpopulation Shift

Yuzhe Yang, Haoran Zhang, Dina Katabi, Marzyeh Ghassemi

Comments ICML 2023

Unsupervised Out-of-Distribution Detection with Diffusion Inpainting

Zhenzhen Liu, Jin Peng Zhou, Yufan Wang, Kilian Q. Weinberger

Comments ICML 2023

Markovian Gaussian Process Variational Autoencoders

Harrison Zhu, Carles Balsells Rodas, Yingzhen Li

Comments Conference paper published at ICML 2023 https://openreview.net/pdf?id=Z8QlQ207V6

Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks

Winfried Lötzsch, Simon Ohler, Johannes S. Otterbach

Journal ref 2nd AI4Science Workshop at the 39th International Conference on Machine Learning (ICML), 2022

Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition

Dongqi Cai, Yangyuxuan Kang, Anbang Yao, Yurong Chen

Comments The paper of Ske2Grid is published at ICML 2023. Code and models are available at https://github.com/OSVAI/Ske2Grid

Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alerts

Guillermo Cabrera-Vives, César Bolivar, Francisco Förster, Alejandra M. Muñoz Arancibia, Manuel Pérez-Carrasco, Esteban Reyes

Journal ref ICML 2023 Workshop on Machine Learning for Astrophysics

Policy Regularization with Dataset Constraint for Offline Reinforcement Learning

Yuhang Ran, Yi-Chen Li, Fuxiang Zhang, Zongzhang Zhang, Yang Yu

Comments Accepted to ICML 2023

Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization

Chris Junchi Li, Angela Yuan, Gauthier Gidel, Quanquan Gu, Michael I. Jordan

Comments 44 pages. This version matches the camera-ready that appeared at ICML 2023 under the same title

Fair Densities via Boosting the Sufficient Statistics of Exponential Families

Alexander Soen, Hisham Husain, Richard Nock

Comments Published in Proceedings of the 40th International Conference on Machine Learning (ICML2023)

On the Training Instability of Shuffling SGD with Batch Normalization

David X. Wu, Chulhee Yun, Suvrit Sra

Comments ICML 2023 camera-ready version, added references; 75 pages

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford

Comments ICML 2023

Causal Conceptions of Fairness and their Consequences

Hamed Nilforoshan, Johann Gaebler, Ravi Shroff, Sharad Goel

Comments ICML 2022. arXiv admin note: substantial text overlap with arXiv:1808.00023

Journal ref Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data

Cheol Jun Cho, Edward F. Chang, Gopala K. Anumanchipalli

Comments Accepted at ICML 2023

Journal ref Proceedings of the 40th International Conference on Machine Learning (2023), PMLR 202:5661-5676

Positional Encodings for Light Curve Transformers: Playing with Positions and Attention

Daniel Moreno-Cartagena, Guillermo Cabrera-Vives, Pavlos Protopapas, Cristobal Donoso-Oliva, Manuel Pérez-Carrasco, Martina Cádiz-Leyton

Comments In Proceedings of the 40th International Conference on Machine Learning (ICML), Workshop on Machine Learning for Astrophysics, PMLR 202, 2023, Honolulu, Hawaii, USA

Journal ref In Proceedings of the 40th International Conference on Machine Learning (ICML), Workshop on Machine Learning for Astrophysics, PMLR 202, 2023, Honolulu, Hawaii, USA

ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging

Alessandro Fontanella, Antreas Antoniou, Wenwen Li, Joanna Wardlaw, Grant Mair, Emanuele Trucco, Amos Storkey

Comments International Conference on Machine Learning 2023. 17 pages, 7 figures

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10153-10169, 2023

Why Target Networks Stabilise Temporal Difference Methods

Mattie Fellows, Matthew J. A. Smith, Shimon Whiteson

Comments Found a small error in Appendix (Proposition 1, Appendix B3, penultimate line) that affects results presented in the original submission. These have been fixed and this version is the one accepted at ICML 2023

Journal ref ICML 2023

Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks

Kenta Oono, Taiji Suzuki

Comments Version 4: Fixed the constant B^{(fc)} in Theorems 1, 5 and the norm upper bound of w^{(l)}_m in Lemma 1. 8 pages + References 2 pages + Supplemental material 18 pages

Journal ref Proceedings of the 36th International Conference on Machine Learning (ICML 2019)

RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows

Shinjan Ghosh, Amit Chakraborty, Georgia Olympia Brikis, Biswadip Dey

Journal ref Published at the 1st workshop on Synergy of Scientific and Machine Learning Modeling, ICML 2023

Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models

Matthew J. Muckley, Alaaeldin El-Nouby, Karen Ullrich, Hervé Jégou, Jakob Verbeek

Comments Upload camera-ready to arXiv. Official version available at https://proceedings.mlr.press/v202/muckley23a.html

Journal ref Proceedings of the 40th International Conference on Machine Learning (2023) 25426-25443

How many perturbations break this model? Evaluating robustness beyond adversarial accuracy

Raphael Olivier, Bhiksha Raj

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26583-26598, 2023

Multi-Class Deep SVDD: Anomaly Detection Approach in Astronomy with Distinct Inlier Categories

Manuel Pérez-Carrasco, Guillermo Cabrera-Vives, Lorena Hernández-García, Francisco Forster, Paula Sánchez-Sáez, Alejandra Muñoz Arancibia, Nicolás Astorga, Franz Bauer, Amelia Bayo, Martina Cádiz-Leyton, Marcio Catelan

Comments Accepted to ICML 2023 Workshop on Machine Learning for Astrophysics

When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis

Yiyou Sun, Zhenmei Shi, Yingyu Liang, Yixuan Li

Comments ICML 2023

Accelerating LLM Inference with Staged Speculative Decoding

Benjamin Spector, Chris Re

Comments Published at ES-FOMO at ICML 2023

An Exact Kernel Equivalence for Finite Classification Models

Brian Bell, Michael Geyer, David Glickenstein, Amanda Fernandez, Juston Moore

Comments TAG-ML at ICML 2023 in Proceedings. 8 pages, 6 figures, proofs in Appendix

Gibbsian polar slice sampling

Philip Schär, Michael Habeck, Daniel Rudolf

Comments 20 pages, 14 figures

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30204-30223, 2023

Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models

Peter Henderson, Eric Mitchell, Christopher D. Manning, Dan Jurafsky, Chelsea Finn

Comments v1 Presented at the First Workshop of Pre-training: Perspectives, Pitfalls, and Paths Forward (ICML, 2022) and New Frontiers in Adversarial Machine Learning Workshop (ICML, 2022); v2 Presented at the Sixth AAAI/ACM Conference on AI, Ethics, and Society (AIES, 2023)

MetAug: Contrastive Learning via Meta Feature Augmentation

Jiangmeng Li, Wenwen Qiang, Changwen Zheng, Bing Su, Hui Xiong

Comments Accepted by ICML 2022

Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage

Catherine Huang, Chelse Swoopes, Christina Xiao, Jiaqi Ma, Himabindu Lakkaraju

Comments Proceedings of The Second Workshop on New Frontiers in Adversarial Machine Learning (AdvML-Frontiers @ ICML 2023)