ICML

Explaining the effects of non-convergent sampling in the training of Energy-Based Models

Elisabeth Agoritsas, Giovanni Catania, Aurélien Decelle, Beatriz Seoane

Comments Accepted at ICML 2023

Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing

Hyeonsu Jeong, Hye Won Chung

Comments ICML 2023

A Generalization of ViT/MLP-Mixer to Graphs

Xiaoxin He, Bryan Hooi, Thomas Laurent, Adam Perold, Yann LeCun, Xavier Bresson

Comments In Proceedings of ICML 2023

X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion

Hanqing Zhao, Dianmo Sheng, Jianmin Bao, Dongdong Chen, Dong Chen, Fang Wen, Lu Yuan, Ce Liu, Wenbo Zhou, Qi Chu, Weiming Zhang, Nenghai Yu

Comments ICML 2023, code is available at https://github.com/yoctta/XPaste

Pareto Regret Analyses in Multi-objective Multi-armed Bandit

Mengfan Xu, Diego Klabjan

Comments 19 pages; accepted at ICML 2023 and to be published in Proceedings of Machine Learning Research (PMLR)

Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature

Khang Nguyen, Hieu Nong, Vinh Nguyen, Nhat Ho, Stanley Osher, Tan Nguyen

Comments Accepted at ICML 2023; 24 pages, 4 figures

Deep Regression Unlearning

Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Mohan Kankanhalli

Comments Accepted in ICML 2023

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

Stone Tao, Xiaochen Li, Tongzhou Mu, Zhiao Huang, Yuzhe Qin, Hao Su

Comments ICML 2023. Code and visualizations: https://trajectorytranslation.github.io/

Variational Open-Domain Question Answering

Valentin Liévin, Andreas Geert Motzfeldt, Ida Riis Jensen, Ole Winther

Comments 28 pages, 5 figures. Accepted at ICML 2023

Why Random Pruning Is All We Need to Start Sparse

Advait Gadhikar, Sohom Mukherjee, Rebekka Burkholz

Comments Accepted for publication at ICML, 2023

Implicit Neural Spatial Representations for Time-dependent PDEs

Honglin Chen, Rundi Wu, Eitan Grinspun, Changxi Zheng, Peter Yichen Chen

Comments ICML 2023. Project page: http://www.cs.columbia.edu/cg/INSR-PDE/

FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning

Songtao Liu, Zhengkai Tu, Minkai Xu, Zuobai Zhang, Lu Lin, Rex Ying, Jian Tang, Peilin Zhao, Dinghao Wu

Comments Accepted by ICML 2023

ILLUME: Rationalizing Vision-Language Models through Human Interactions

Manuel Brack, Patrick Schramowski, Björn Deiseroth, Kristian Kersting

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

IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound

Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth

Comments ICML 2022 Workshop on Formal Verification of Machine Learning

FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction

Yongxin Guo, Xiaoying Tang, Tao Lin

Comments Accepted by International Conference on Machine Learning (ICML2023)

On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation

Maohao Shen, Yuheng Bu, Gregory Wornell

Comments ICML 2023

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

Ming Li, Sho Sonoda, Feilong Cao, Yu Guang Wang, Jiye Liang

Comments Published as a conference paper at ICML 2023

FedDisco: Federated Learning with Discrepancy-Aware Collaboration

Rui Ye, Mingkai Xu, Jianyu Wang, Chenxin Xu, Siheng Chen, Yanfeng Wang

Comments Accepted by International Conference on Machine Learning (ICML2023)

Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks

Qiyu Kang, Kai Zhao, Yang Song, Sijie Wang, Wee Peng Tay

Journal ref International Conference on Machine Learning, 2023

Subequivariant Graph Reinforcement Learning in 3D Environments

Runfa Chen, Jiaqi Han, Fuchun Sun, Wenbing Huang

Comments ICML 2023 Oral

How Does Information Bottleneck Help Deep Learning?

Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang Huang

Comments Accepted at ICML 2023. Code is available at https://github.com/xu-ji/information-bottleneck

Learning Perturbations to Explain Time Series Predictions

Joseph Enguehard

Comments Accepted at ICML 2023

Shapley Based Residual Decomposition for Instance Analysis

Tommy Liu, Amanda Barnard

Comments Accepted, 40th International Conference on Machine Learning

Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition

Boran Han

Comments accepted by ICML 2023

Predicting Rare Events by Shrinking Towards Proportional Odds

Gregory Faletto, Jacob Bien

Comments 84 pages, 20 figures. Accepted at the Fortieth International Conference on Machine Learning (ICML 2023)

Towards Constituting Mathematical Structures for Learning to Optimize

Jialin Liu, Xiaohan Chen, Zhangyang Wang, Wotao Yin, HanQin Cai

Comments ICML 2023

The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation

Mark Rowland, Yunhao Tang, Clare Lyle, Rémi Munos, Marc G. Bellemare, Will Dabney

Comments ICML 2023

Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching

Ilgee Hong, Sen Na, Michael W. Mahoney, Mladen Kolar

Comments 25 pages, 4 figures

Journal ref ICML 2023

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

Tianqi Chen, Mingyuan Zhou

Comments ICML 2023

New metrics and search algorithms for weighted causal DAGs

Davin Choo, Kirankumar Shiragur

Comments Accepted into ICML 2023