ICML

Equivariant Quantum Graph Circuits

Péter Mernyei, Konstantinos Meichanetzidis, İsmail İlkan Ceylan

Comments To be presented at ICML 2022 - uploading camera-ready version

Constrained Discrete Black-Box Optimization using Mixed-Integer Programming

Theodore Papalexopoulos, Christian Tjandraatmadja, Ross Anderson, Juan Pablo Vielma, David Belanger

Comments 9 pages, 4 figures, accepted to ICML 2022, appendix with additional results in same file

ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning

Jun Xia, Lirong Wu, Ge Wang, Jintao Chen, Stan Z. Li

Comments Accetpted at ICML 2022

Large Batch Experience Replay

Thibault Lahire, Matthieu Geist, Emmanuel Rachelson

Comments 24 pages, 12 figures, ICML 2022 - long presentation

Learning Domain Adaptive Object Detection with Probabilistic Teacher

Meilin Chen, Weijie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Yunfeng Yan, Donglian Qi, Yueting Zhuang, Di Xie, Shiliang Pu

Comments To appear in ICML 2022. Code is coming soon: https://github.com/hikvision-research/ProbabilisticTeacher

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

Towards Understanding Sharpness-Aware Minimization

Maksym Andriushchenko, Nicolas Flammarion

Comments The camera-ready version (accepted at ICML 2022)

Data-SUITE: Data-centric identification of in-distribution incongruous examples

Nabeel Seedat, Jonathan Crabbé, Mihaela van der Schaar

Comments Presented at the International Conference on Machine Learning (ICML) 2022

Structure-Aware Transformer for Graph Representation Learning

Dexiong Chen, Leslie O'Bray, Karsten Borgwardt

Comments To appear in ICML 2022

On the Adversarial Robustness of Causal Algorithmic Recourse

Ricardo Dominguez-Olmedo, Amir-Hossein Karimi, Bernhard Schölkopf

Comments ICML 2022

Interactive Inverse Reinforcement Learning for Cooperative Games

Thomas Kleine Buening, Anne-Marie George, Christos Dimitrakakis

Comments ICML 2022

Neural Tangent Kernel Empowered Federated Learning

Kai Yue, Richeng Jin, Ryan Pilgrim, Chau-Wai Wong, Dror Baron, Huaiyu Dai

Comments Accepted by ICML 2022

Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling

Yuanbang Liang, Jing Wu, Yu-Kun Lai, Yipeng Qin

Comments Accepted at ICML 2022. Our code is available at: https://github.com/Byronliang8/HubnessGANSampling

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations

Mohammad Mahmudul Alam, Edward Raff, Tim Oates, James Holt

Comments To appear in the Proceedings of the 39 th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

Rare event failure test case generation in Learning-Enabled-Controllers

Harsh Vardhan, Janos Sztipanovits

Journal ref 2021 6th International Conference on Machine Learning Technologies

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering

Ekdeep Singh Lubana, Chi Ian Tang, Fahim Kawsar, Robert P. Dick, Akhil Mathur

Comments Camera-ready ICML, 2022

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi

Comments International Conference on Machine Learning (ICML), 2022

Fast Rates in Pool-Based Batch Active Learning

Claudio Gentile, Zhilei Wang, Tong Zhang

Comments This is an extended version of arXiv:2202.05448v1, which has title "Achieving Minimax Rates in Pool-Based Batch Active Learning" and was accepted by ICML 2022 https://icml.cc/virtual/2022/poster/16505

Imitation Learning by Estimating Expertise of Demonstrators

Mark Beliaev, Andy Shih, Stefano Ermon, Dorsa Sadigh, Ramtin Pedarsani

Comments ICML 2022. 17 pages, 4 figures

Improving Screening Processes via Calibrated Subset Selection

Lequn Wang, Thorsten Joachims, Manuel Gomez Rodriguez

Comments International Conference on Machine Learning (ICML) 2022

Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits

Aadirupa Saha, Shubham Gupta

Comments Accepted to International Conference on Machine Learning (ICML), 2022 [both authors contributed equally]

Tight and Robust Private Mean Estimation with Few Users

Hossein Esfandiari, Vahab Mirrokni, Shyam Narayanan

Comments 41 pages. To appear in the International Conference on Machine Learning (ICML), 2022

Improving Transformers with Probabilistic Attention Keys

Tam Nguyen, Tan M. Nguyen, Dung D. Le, Duy Khuong Nguyen, Viet-Anh Tran, Richard G. Baraniuk, Nhat Ho, Stanley J. Osher

Comments 27 pages, 16 figures, 10 tables

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

Cycle Representation Learning for Inductive Relation Prediction

Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen

Comments Accepted in ICML 2022

Communicating via Markov Decision Processes

Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl, Luisa Zintgraf, Philip Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob Foerster

Comments ICML 2022

Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation

Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon

Comments 28 pages, 16 figures, 15 tables

Journal ref International Conference on Machine Learning (ICML) 2022

Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures

Nelson Vadori, Rahul Savani, Thomas Spooner, Sumitra Ganesh

Comments ICML 2022, the 39th International Conference on Machine Learning

Few-Shot Keyword Spotting With Prototypical Networks

Archit Parnami, Minwoo Lee

Journal ref 2022 7th International Conference on Machine Learning Technologies (ICMLT), ACM, pages 277-283

Interactively Learning Preference Constraints in Linear Bandits

David Lindner, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause

Comments Accepted to International Conference on Machine Learning (ICML), 2022

Scalable Deep Gaussian Markov Random Fields for General Graphs

Joel Oskarsson, Per Sidén, Fredrik Lindsten

Comments 22 pages, 10 figures. Accepted at ICML 2022. Code available at https://github.com/joeloskarsson/graph-dgmrf

Data-Efficient Double-Win Lottery Tickets from Robust Pre-training

Tianlong Chen, Zhenyu Zhang, Sijia Liu, Yang Zhang, Shiyu Chang, Zhangyang Wang

Comments Accepted by ICML 2022