ICML

Causal Modeling of Policy Interventions From Sequences of Treatments and Outcomes

Çağlar Hızlı, ST John, Anne Juuti, Tuure Saarinen, Kirsi Pietiläinen, Pekka Marttinen

Comments Accepted at ICML 2023

Simple and Fast Group Robustness by Automatic Feature Reweighting

Shikai Qiu, Andres Potapczynski, Pavel Izmailov, Andrew Gordon Wilson

Comments ICML 23. Code available at https://github.com/AndPotap/afr

Journal ref 40th International Conference on Machine Learning 2023

Scaling of Class-wise Training Losses for Post-hoc Calibration

Seungjin Jung, Seungmo Seo, Yonghyun Jeong, Jongwon Choi

Comments Published at ICML 2023. Camera ready version

Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification

Dong Xing, Pengjie Gu, Qian Zheng, Xinrun Wang, Shanqi Liu, Longtao Zheng, Bo An, Gang Pan

Comments Accepted by ICML 2023

BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming

Steven Adams, Andrea Patane, Morteza Lahijanian, Luca Laurenti

Comments To appear at ICML 2023

Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation

Qianru Zhang, Chao Huang, Lianghao Xia, Zheng Wang, Siuming Yiu, Ruihua Han

Comments This paper is accepted by ICML 2023

On Distribution Dependent Sub-Logarithmic Query Time of Learned Indexing

Sepanta Zeighami, Cyrus Shahabi

Comments Proceedings of 40th International Conference on Machine Learning, ICML 2023

Stabilizing GANs' Training with Brownian Motion Controller

Tianjiao Luo, Ziyu Zhu, Jianfei Chen, Jun Zhu

Journal ref Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023. Copyright 2023 by the author(s)

Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models

Ajay Jaiswal, Shiwei Liu, Tianlong Chen, Ying Ding, Zhangyang Wang

Comments Accepted in ICML 2023

Weakly Supervised Regression with Interval Targets

Xin Cheng, Yuzhou Cao, Ximing Li, Bo An, Lei Feng

Comments Accepted by ICML 2023

Bootstrapped Representations in Reinforcement Learning

Charline Le Lan, Stephen Tu, Mark Rowland, Anna Harutyunyan, Rishabh Agarwal, Marc G. Bellemare, Will Dabney

Comments ICML 2023

EM-Network: Oracle Guided Self-distillation for Sequence Learning

Ji Won Yoon, Sunghwan Ahn, Hyeonseung Lee, Minchan Kim, Seok Min Kim, Nam Soo Kim

Comments ICML 2023

From Hypergraph Energy Functions to Hypergraph Neural Networks

Yuxin Wang, Quan Gan, Xipeng Qiu, Xuanjing Huang, David Wipf

Comments Accepted to ICML 2023

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen

Comments ICML 2023

TIPS: Topologically Important Path Sampling for Anytime Neural Networks

Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu

Comments ICML 2023

Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries

Charlotte Loh, Seungwook Han, Shivchander Sudalairaj, Rumen Dangovski, Kai Xu, Florian Wenzel, Marin Soljacic, Akash Srivastava

Comments Camera Ready Revision. ICML 2023

Self-supervised learning of Split Invariant Equivariant representations

Quentin Garrido, Laurent Najman, Yann Lecun

Journal ref The Fortieth International Conference on Machine Learning, 2023, Honolulu, United States

Domain Adaptation for Time Series Under Feature and Label Shifts

Huan He, Owen Queen, Teddy Koker, Consuelo Cuevas, Theodoros Tsiligkaridis, Marinka Zitnik

Comments Accepted by ICML 2023; 29 pages (14 pages main paper + 15 pages supplementary materials). Code: see https://github.com/mims-harvard/Raincoat

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Ling Pan, Nikolay Malkin, Dinghuai Zhang, Yoshua Bengio

Comments ICML 2023

Input Perturbation Reduces Exposure Bias in Diffusion Models

Mang Ning, Enver Sangineto, Angelo Porrello, Simone Calderara, Rita Cucchiara

Comments accepted by ICML 2023

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series

Abdul Fatir Ansari, Alvin Heng, Andre Lim, Harold Soh

Comments ICML 2023 Camera Ready Version; Code available at https://github.com/clear-nus/NCDSSM

How Jellyfish Characterise Alternating Group Equivariant Neural Networks

Edward Pearce-Crump

Comments ICML 2023 Poster; 13 pages. arXiv admin note: text overlap with arXiv:2212.08648, arXiv:2212.08630

Understanding the Complexity Gains of Single-Task RL with a Curriculum

Qiyang Li, Yuexiang Zhai, Yi Ma, Sergey Levine

Comments 40 pages, 11 Figures, 13 Tables, International Conference on Machine Learning (ICML) 2023

Brauer's Group Equivariant Neural Networks

Edward Pearce-Crump

Comments ICML 2023 OralPoster; 22 pages

Bootstrap in High Dimension with Low Computation

Henry Lam, Zhenyuan Liu

Comments Accepted to Proceedings of the 40th International Conference on Machine Learning (ICML)

Repository-Level Prompt Generation for Large Language Models of Code

Disha Shrivastava, Hugo Larochelle, Daniel Tarlow

Comments ICML 2023 (Camera-Ready version)

Journal ref ICML, 2023

Private Hypothesis Testing for Social Sciences

Ajinkya K Mulay, Sean Lane, Erin Hennes

Comments There are no significant alterations from version 1. We mistakenly included metadata from a journal Latex template while using its document class and it's now removed to avoid any confusion. This article has been accepted at the Workshop on Theory and Practice of Differential Privacy at ICML 2022

Nearly-Optimal Hierarchical Clustering for Well-Clustered Graphs

Steinar Laenen, Bogdan-Adrian Manghiuc, He Sun

Comments This work is accepted at the 40th International Conference on Machine Learning (ICML'23)

Subset Selection Based On Multiple Rankings in the Presence of Bias: Effectiveness of Fairness Constraints for Multiwinner Voting Score Functions

Niclas Boehmer, L. Elisa Celis, Lingxiao Huang, Anay Mehrotra, Nisheeth K. Vishnoi

Comments The conference version of this paper appears in ICML 2023

Understanding the Role of Feedback in Online Learning with Switching Costs

Duo Cheng, Xingyu Zhou, Bo Ji

Comments Accepted to ICML 2023