ICML

RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples

Hossein Mirzaei, Mohammad Jafari, Hamid Reza Dehbashi, Ali Ansari, Sepehr Ghobadi, Masoud Hadi, Arshia Soltani Moakhar, Mohammad Azizmalayeri, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban

Comments Accepted at the Forty-First International Conference on Machine Learning (ICML) 2024. The implementation of our work is available at: \url{https://github.com/rohban-lab/RODEO}

Reconciling Predictive Multiplicity in Practice

Tina Behzad, Sílvia Casacuberta, Emily Ruth Diana, Alexander Williams Tolbert

Comments Presented at the ICML workshop on Humans, Algorithmic Decision-Making and Society: Modeling Interactions and Impact 2024

Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization

Tianyi Lin, Chi Jin, Michael. I. Jordan

Comments Accepted by Journal of Machine Learning Research; A preliminary version [arXiv:1906.00331] of this paper, with a subset of the results that are presented here, was presented at ICML 2020; 44 Pages, 10 Figures

Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning

Zijian Guo, Weichao Zhou, Wenchao Li

Comments Published in ICML 2024

Exact Soft Analytical Side-Channel Attacks using Tractable Circuits

Thomas Wedenig, Rishub Nagpal, Gaëtan Cassiers, Stefan Mangard, Robert Peharz

Comments ICML 2024 Conference Paper

The Goofus & Gallant Story Corpus for Practical Value Alignment

Md Sultan Al Nahian, Tasmia Tasrin, Spencer Frazier, Mark Riedl, Brent Harrison

Comments Accepted by International Conference on Machine Learning and Applications (ICMLA) 2024. Main Conference, Long Paper

KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions

Fabian Fumagalli, Maximilian Muschalik, Patrick Kolpaczki, Eyke Hüllermeier, Barbara Hammer

Comments Published Paper at ICML 2024: https://openreview.net/forum?id=d5jXW2H4gg

Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Proceedings of Machine Learning Research 235:14308-14342, 2024

Interpreting Equivariant Representations

Andreas Abildtrup Hansen, Anna Calissano, Aasa Feragen

Comments This paper was updated to reflect the version accepted to ICML 2024

Journal ref Proceedings of the 41st International Conference on Machine Learning (Vol. 235, pp. 17538-17553, 2024). Proceedings of Machine Learning Research

On The Statistical Complexity of Offline Decision-Making

Thanh Nguyen-Tang, Raman Arora

Comments arXiv version for the ICML'24 paper

On the Complexity of Decentralized Smooth Nonconvex Finite-Sum Optimization

Luo Luo, Yunyan Bai, Lesi Chen, Yuxing Liu, Haishan Ye

Comments A major revision which significantly improves the results by considering the global smoothness parameters and involving the content of PL condition in ICML paper

Towards General Neural Surrogate Solvers with Specialized Neural Accelerators

Chenkai Mao, Robert Lupoiu, Tianxiang Dai, Mingkun Chen, Jonathan A. Fan

Comments 9 pages, 7 Figures, to be published in ICML 2024

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34693-34711, 2024

Safe Reinforcement Learning with Minimal Supervision

Alexander Quessy, Thomas Richardson, Sebastian East

Comments Initially submitted to ICML 2023

MultiMax: Sparse and Multi-Modal Attention Learning

Yuxuan Zhou, Mario Fritz, Margret Keuper

Comments Accepted at ICML 2024

Strategic Fusion Optimizes Transformer Compression

Md Shoaibur Rahman

Comments 15 pages, 1 table, 8 figures; will be submitted to ICML 2025; codes will be made public after acceptance

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition

Hao Fei, Shengqiong Wu, Wei Ji, Hanwang Zhang, Meishan Zhang, Mong-Li Lee, Wynne Hsu

Comments Accepted by ICML 2024

An Advanced Physics-Informed Neural Operator for Comprehensive Design Optimization of Highly-Nonlinear Systems: An Aerospace Composites Processing Case Study

Milad Ramezankhani, Anirudh Deodhar, Rishi Yash Parekh, Dagnachew Birru

Comments Accepted at the ICML 2024 Workshop on AI for Science: Scaling in AI for Scientific Discovery

An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming

Minkai Xu, Wujie Wang, Shitong Luo, Chence Shi, Yoshua Bengio, Rafael Gomez-Bombarelli, Jian Tang

Comments Accepted by ICML 2021

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models

Mengting Ai, Tianxin Wei, Yifan Chen, Zeming Guo, Jingrui He

Comments v1 accepted to ICML 2023. This work has been submitted to the IEEE for possible publication

Partial Identifiability for Domain Adaptation

Lingjing Kong, Shaoan Xie, Weiran Yao, Yujia Zheng, Guangyi Chen, Petar Stojanov, Victor Akinwande, Kun Zhang

Comments ICML 2022; typo corrections

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations

Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan Celine Lin

Comments Accepted by ICML 2023

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Celine Lin

Comments Accepted at ICML 2022

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators

Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox, Yingyan Celine Lin

Comments Accepted at ICML 2021

A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness

Xiaochuan Gong, Jie Hao, Mingrui Liu

Comments ICML 2024

Uncertainty Quantified Deep Learning and Regression Analysis Framework for Image Segmentation of Skin Cancer Lesions

Elhoucine Elfatimi, Pratik Shah

Comments Presented at the 2024 IEEE International Conference on Machine Learning and Applications (ICMLA), accepted for publication and in press by IEEE

Deep Learning with Uncertainty Quantification for Predicting the Segmentation Dice Coefficient of Prostate Cancer Biopsy Images

Audrey Xie, Elhoucine Elfatimi, Sambuddha Ghosal, Pratik Shah

Comments Presented at the 2024 IEEE International Conference on Machine Learning and Applications (ICMLA), accepted for publication and in press by IEEE

Toward Adaptive Reasoning in Large Language Models with Thought Rollback

Sijia Chen, Baochun Li

Comments ICML 2024 camera-ready version with 24 pages and 12 figures. Code repo with all prompts: https://github.com/iQua/llmpebase/tree/main/examples/ThoughtRollback

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones

Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas, Joao Monteiro, Valentina Zantedeschi

Comments Appeared at ICML 2024 Workshop on Efficient Systems for Foundation Models (ES-FoMo-II)

Policy Gradients for Optimal Parallel Tempering MCMC

Daniel Zhao, Natesh S. Pillai

Comments 12 pages, 5 figures, accepted to ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling

DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems

Kaibo He, Chenhui Zuo, Chengtian Ma, Yanan Sui

Comments ICML 2024

Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling

Mingze Wang, Zeping Min, Lei Wu

Comments 37 pages, accepted by ICML 2024