ICML

Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens

Ross M. Clarke, José Miguel Hernández-Lobato

Comments 33 pages, 21 figures, 7 tables. Published at ICML 2024

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

Samuel Horvath, Stefanos Laskaridis, Shashank Rajput, Hongyi Wang

Comments Accepted at the 41st International Conference on Machine Learning (ICML 2024)

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers

Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang

Comments ICML 2024. Code: https://github.com/sdc17/CrossGET

HyperFields: Towards Zero-Shot Generation of NeRFs from Text

Sudarshan Babu, Richard Liu, Avery Zhou, Michael Maire, Greg Shakhnarovich, Rana Hanocka

Comments Accepted to ICML 2024, Project page: https://threedle.github.io/hyperfields/

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret

Han Zhong, Jiachen Hu, Yecheng Xue, Tongyang Li, Liwei Wang

Comments ICML 2024

Dynamic Correlation Clustering in Sublinear Update Time

Vincent Cohen-Addad, Silvio Lattanzi, Andreas Maggiori, Nikos Parotsidis

Comments ICML'24 (spotlight)

Neural NeRF Compression

Tuan Pham, Stephan Mandt

Comments Accepted to ICML 2024

Roping in Uncertainty: Robustness and Regularization in Markov Games

Jeremy McMahan, Giovanni Artiglio, Qiaomin Xie

Comments Accepted to ICML 2024

Feasibility Consistent Representation Learning for Safe Reinforcement Learning

Zhepeng Cen, Yihang Yao, Zuxin Liu, Ding Zhao

Comments ICML 2024

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

Comments ICML 2024. Project page: https://ins-rl.github.io/

CLLMs: Consistency Large Language Models

Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, Hao Zhang

Comments In the proceedings of the 41st International Conference on Machine Learning (ICML) 2024

Predictive Linear Online Tracking for Unknown Targets

Anastasios Tsiamis, Aren Karapetyan, Yueshan Li, Efe C. Balta, John Lygeros

Comments ICML 2024 (spotlight)

LESS: Selecting Influential Data for Targeted Instruction Tuning

Mengzhou Xia, Sadhika Malladi, Suchin Gururangan, Sanjeev Arora, Danqi Chen

Comments ICML 2024; Code and data are available at https://github.com/princeton-nlp/LESS

Gaussian Plane-Wave Neural Operator for Electron Density Estimation

Seongsu Kim, Sungsoo Ahn

Comments Accepted by ICML 2024 main poster

Journal ref International Conference on Machine Learning (ICML), 2024

Flora: Low-Rank Adapters Are Secretly Gradient Compressors

Yongchang Hao, Yanshuai Cao, Lili Mou

Comments Accepted @ ICML 2024

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li

Comments Accepted at ICML 2024

When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions

Zhening Li, Gabriel Poesia, Armando Solar-Lezama

Comments 29 pages, 1 figure. Accepted to ICML 2024

KernelWarehouse: Rethinking the Design of Dynamic Convolution

Chao Li, Anbang Yao

Comments This work is accepted to ICML 2024. The project page: https://github.com/OSVAI/KernelWarehouse. arXiv admin note: substantial text overlap with arXiv:2308.08361

The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm

Giseung Park, Woohyeon Byeon, Seongmin Kim, Elad Havakuk, Amir Leshem, Youngchul Sung

Comments Accepted to ICML 2024

Predictive Performance Comparison of Decision Policies Under Confounding

Luke Guerdan, Amanda Coston, Kenneth Holstein, Zhiwei Steven Wu

Comments ICML 2024

Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs

S. Chandra Mouli, Danielle C. Maddix, Shima Alizadeh, Gaurav Gupta, Andrew Stuart, Michael W. Mahoney, Yuyang Wang

Comments ICML 2024

Shifted Interpolation for Differential Privacy

Jinho Bok, Weijie Su, Jason M. Altschuler

Comments 45 pages, ICML 2024. v2: added lower bounds (Appendix C.5)

Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning

Jin Hwa Lee, Stefano Sarao Mannelli, Andrew Saxe

Comments Accepted to ICML 2024. 5 figures, 9 pages and Appendix

Batch and match: black-box variational inference with a score-based divergence

Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul

Comments 49 pages, 14 figures. To appear in the Proceedings of the 41st International Conference on Machine Learning (ICML), 2024

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks

Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri, Lucas Saldyt, Anil Murthy

Journal ref Proceedings of the 41 st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024

Multi-group Learning for Hierarchical Groups

Samuel Deng, Daniel Hsu

Comments Accepted in International Conference on Machine Learning 2024 (ICML 2024). Fixed reference description in "Related Work" for multi-task learning

Emergence of In-Context Reinforcement Learning from Noise Distillation

Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov

Comments Proceedings of the 41-st International Conference on Machine Learning (ICML 2024); code: https://github.com/corl-team/ad-eps

Low-Cost High-Power Membership Inference Attacks

Sajjad Zarifzadeh, Philippe Liu, Reza Shokri

Comments ICML 2024

A Geometric Explanation of the Likelihood OOD Detection Paradox

Hamidreza Kamkari, Brendan Leigh Ross, Jesse C. Cresswell, Anthony L. Caterini, Rahul G. Krishnan, Gabriel Loaiza-Ganem

Comments ICML 2024

Transferring Knowledge from Large Foundation Models to Small Downstream Models

Shikai Qiu, Boran Han, Danielle C. Maddix, Shuai Zhang, Yuyang Wang, Andrew Gordon Wilson

Comments ICML 2024. Code available at https://github.com/amazon-science/adaptive-feature-transfer