ICML

Generative Flow Networks for Discrete Probabilistic Modeling

Dinghuai Zhang, Nikolay Malkin, Zhen Liu, Alexandra Volokhova, Aaron Courville, Yoshua Bengio

Comments Accepted by ICML 2022

A Self-Supervised Automatic Post-Editing Data Generation Tool

Hyeonseok Moon, Chanjun Park, Sugyeong Eo, Jaehyung Seo, SeungJun Lee, Heuiseok Lim

Comments Accepted for DataPerf workshop at ICML 2022

Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses

Keegan Harris, Daniel Ngo, Logan Stapleton, Hoda Heidari, Zhiwei Steven Wu

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

Selective Network Linearization for Efficient Private Inference

Minsu Cho, Ameya Joshi, Siddharth Garg, Brandon Reagen, Chinmay Hegde

Comments Published in ICML 2022

Inverse Contextual Bandits: Learning How Behavior Evolves over Time

Alihan Hüyük, Daniel Jarrett, Mihaela van der Schaar

Comments In Proceedings of the 39th International Conference on Machine Learning

Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations

Ziquan Liu, Yufei Cui, Antoni B. Chan

Comments 14 pages, 5 figures, Accepted by ICML 2021 Workshop on Adversarial Machine Learning

Building Robust Ensembles via Margin Boosting

Dinghuai Zhang, Hongyang Zhang, Aaron Courville, Yoshua Bengio, Pradeep Ravikumar, Arun Sai Suggala

Comments Accepted by ICML 2022

Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images

Tom Ron, Michal Weiler-Sagie, Tamir Hazan

Comments 12 pages, 5 figures. In proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022. Copyright 2022 by the author(s)

Reachability Constrained Reinforcement Learning

Dongjie Yu, Haitong Ma, Shengbo Eben Li, Jianyu Chen

Comments Accepted by ICML 2022

Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks

Zhaoning Yu, Hongyang Gao

Comments International Conference on Machine Learning (2022)

Improving Mini-batch Optimal Transport via Partial Transportation

Khai Nguyen, Dang Nguyen, The-Anh Vu-Le, Tung Pham, Nhat Ho

Comments Accepted to ICML 2022, 36 pages, 18 figures, 18 tables

On Transportation of Mini-batches: A Hierarchical Approach

Khai Nguyen, Dang Nguyen, Quoc Nguyen, Tung Pham, Hung Bui, Dinh Phung, Trung Le, Nhat Ho

Comments Accepted to ICML 2022, 34 pages, 16 figures, 9 tables

The CLRS Algorithmic Reasoning Benchmark

Petar Veličković, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell

Comments To appear in ICML 2022. 19 pages, 4 figures

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

Hannes Stärk, Octavian-Eugen Ganea, Lagnajit Pattanaik, Regina Barzilay, Tommi Jaakkola

Comments 39th International Conference on Machine Learning (ICML 2022). Also accepted at ICLR 2022 GTRL and at ICLR 2022 MLDD as spotlight

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

Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

Tianwei Ni, Benjamin Eysenbach, Ruslan Salakhutdinov

Comments ICML 2022 camera ready version. Code: https://github.com/twni2016/pomdp-baselines Project site: https://sites.google.com/view/pomdp-baselines

Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters

Vladislav Kurenkov, Sergey Kolesnikov

Comments ICML 2022, Spotlight; https://tinkoff-ai.github.io/eop/

3D Infomax improves GNNs for Molecular Property Prediction

Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Liò

Comments 39th International Conference on Machine Learning (ICML 2022). Also accepted at NeurIPS 2021 ML4PH, AI4S, and SSL workshops and as oral at ELLIS ML4Molecules. 24 pages, 7 figures, 18 tables

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

Learning from Counterfactual Links for Link Prediction

Tong Zhao, Gang Liu, Daheng Wang, Wenhao Yu, Meng Jiang

Comments Accepted by ICML 2022

Causal Transformer for Estimating Counterfactual Outcomes

Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

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

Robust Multi-Objective Bayesian Optimization Under Input Noise

Samuel Daulton, Sait Cakmak, Maximilian Balandat, Michael A. Osborne, Enlu Zhou, Eytan Bakshy

Comments To appear at ICML 2022. 36 pages. Code is available at https://github.com/facebookresearch/robust_mobo

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, C. Lawrence Zitnick

Comments Published as a conference paper at ICML 2019. This version contains supplementary appendices

Continuous Control with Action Quantization from Demonstrations

Robert Dadashi, Léonard Hussenot, Damien Vincent, Sertan Girgin, Anton Raichuk, Matthieu Geist, Olivier Pietquin

Comments Accepted to ICML 2022

Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning

Andrea Zanette, Martin J. Wainwright

Comments Appears in ICML 2022

Dataset Condensation via Efficient Synthetic-Data Parameterization

Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh, Sangdoo Yun, Hwanjun Song, Joonhyun Jeong, Jung-Woo Ha, Hyun Oh Song

Comments ICML 2022; Codes at https://github.com/snu-mllab/Efficient-Dataset-Condensation.git

Leveraging Non-uniformity in First-order Non-convex Optimization

Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvari, Dale Schuurmans

Comments 48 pages, 10 figures. Accepted at ICML 2021

On the Global Convergence Rates of Softmax Policy Gradient Methods

Jincheng Mei, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans

Comments 64 pages, 5 figures. Published in ICML 2020

Privacy for Free: How does Dataset Condensation Help Privacy?

Tian Dong, Bo Zhao, Lingjuan Lyu

Comments Accepted by ICML 2022 as Oral

Easy Variational Inference for Categorical Models via an Independent Binary Approximation

Michael T. Wojnowicz, Shuchin Aeron, Eric L. Miller, Michael C. Hughes

Comments to appear at ICML 2022

Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback

Tianyi Lin, Aldo Pacchiano, Yaodong Yu, Michael I. Jordan

Comments Accepted by ICML 2022; The first three authors contributed equally to this work; 36 pages, 9 figures

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts

Yan Zeng, Xinsong Zhang, Hang Li

Comments ICML 2022