ICML

Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces

Javier E Santos, Zachary R. Fox, Nicholas Lubbers, Yen Ting Lin

Comments 29 pages, 13 figures, 2 tables. Accepted by the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA

DRew: Dynamically Rewired Message Passing with Delay

Benjamin Gutteridge, Xiaowen Dong, Michael Bronstein, Francesco Di Giovanni

Comments Accepted at ICML 2023; 16 pages

CLUSTSEG: Clustering for Universal Segmentation

James Liang, Tianfei Zhou, Dongfang Liu, Wenguan Wang

Comments Accepted to ICML 2023; Code: https://github.com/JamesLiang819/ClustSeg

Expected Gradients of Maxout Networks and Consequences to Parameter Initialization

Hanna Tseran, Guido Montúfar

Comments Published at ICML 2023, 42 pages, 11 figures

A Study on Transformer Configuration and Training Objective

Fuzhao Xue, Jianghai Chen, Aixin Sun, Xiaozhe Ren, Zangwei Zheng, Xiaoxin He, Yongming Chen, Xin Jiang, Yang You

Comments Accepted at ICML 2023

Model-Free Robust Average-Reward Reinforcement Learning

Yue Wang, Alvaro Velasquez, George Atia, Ashley Prater-Bennette, Shaofeng Zou

Comments ICML 2023

Reinforcement Learning with History-Dependent Dynamic Contexts

Guy Tennenholtz, Nadav Merlis, Lior Shani, Martin Mladenov, Craig Boutilier

Comments Published in ICML 2023

Unifying Molecular and Textual Representations via Multi-task Language Modelling

Dimitrios Christofidellis, Giorgio Giannone, Jannis Born, Ole Winther, Teodoro Laino, Matteo Manica

Comments ICML 2023

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

Wenfang Sun, Yingjun Du, Xiantong Zhen, Fan Wang, Ling Wang, Cees G. M. Snoek

Comments Accepted by ICML 2023

Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphs

Daniel Severo, James Townsend, Ashish Khisti, Alireza Makhzani

Comments Published at ICML 2023

Motion Question Answering via Modular Motion Programs

Mark Endo, Joy Hsu, Jiaman Li, Jiajun Wu

Comments In ICML 2023; first two authors contributed equally to this work

$π$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation

Chengyue Wu, Teng Wang, Yixiao Ge, Zeyu Lu, Ruisong Zhou, Ying Shan, Ping Luo

Comments To appear in ICML 2023

Leveraging Demonstrations to Improve Online Learning: Quality Matters

Botao Hao, Rahul Jain, Tor Lattimore, Benjamin Van Roy, Zheng Wen

Comments Accepted at ICML 2023

Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs

Michael Kirchhof, Enkelejda Kasneci, Seong Joon Oh

Comments Accepted at ICML 2023

Anti-Exploration by Random Network Distillation

Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov

Comments ICML 2023, Poster, Source code: https://github.com/tinkoff-ai/sac-rnd

The Hessian perspective into the Nature of Convolutional Neural Networks

Sidak Pal Singh, Thomas Hofmann, Bernhard Schölkopf

Comments ICML 2023 conference proceedings

Moderately Distributional Exploration for Domain Generalization

Rui Dai, Yonggang Zhang, Zhen Fang, Bo Han, Xinmei Tian

Comments Accepted by ICML 2023

Run-Off Election: Improved Provable Defense against Data Poisoning Attacks

Keivan Rezaei, Kiarash Banihashem, Atoosa Chegini, Soheil Feizi

Comments Accepted to ICML 2023

Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback

Tal Lancewicki, Aviv Rosenberg, Dmitry Sotnikov

Comments ICML 2023

Optimal LP Rounding and Linear-Time Approximation Algorithms for Clustering Edge-Colored Hypergraphs

Nate Veldt

Comments Accepted for publication at ICML 2023

On the Convergence of SARSA with Linear Function Approximation

Shangtong Zhang, Remi Tachet, Romain Laroche

Comments ICML 2023

Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization

G. Bruno De Luca, Eva Silverstein

Comments ICML 2022. 9 pages + Appendix, 8 figures. Code available at https://github.com/gbdl/BBI

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:4918-4936, 2022

On the Optimality of Misspecified Kernel Ridge Regression

Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin

Comments 23 pages, 6 figures, The Fortieth International Conference on Machine Learning. arXiv admin note: substantial text overlap with arXiv:2303.14942

Towards Understanding and Improving GFlowNet Training

Max W. Shen, Emmanuel Bengio, Ehsan Hajiramezanali, Andreas Loukas, Kyunghyun Cho, Tommaso Biancalani

Comments Accepted to ICML 2023

Stratified Adversarial Robustness with Rejection

Jiefeng Chen, Jayaram Raghuram, Jihye Choi, Xi Wu, Yingyu Liang, Somesh Jha

Comments Paper published at International Conference on Machine Learning (ICML'23)

AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners

Zhixuan Liang, Yao Mu, Mingyu Ding, Fei Ni, Masayoshi Tomizuka, Ping Luo

Comments Accepted by ICML 2023. Project page: https://adaptdiffuser.github.io

Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning

Yu Meng, Martin Michalski, Jiaxin Huang, Yu Zhang, Tarek Abdelzaher, Jiawei Han

Comments ICML 2023. (Code: https://github.com/yumeng5/FewGen)

Text-To-Concept (and Back) via Cross-Model Alignment

Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi

Comments Accepted to ICML 2023 and CVPR4XAI workshop 2023

Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering

Mingqi Yang, Wenjie Feng, Yanming Shen, Bryan Hooi

Comments ICML 2023

Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers

Grant P. Strimel, Yi Xie, Brian King, Martin Radfar, Ariya Rastrow, Athanasios Mouchtaris

Comments Accepted to ICML 2023