ICML

Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping

Ben Lonnqvist, Zhengqing Wu, Michael H. Herzog

Comments ICML 2024 camera ready version

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

Zongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li

Comments ICML 2024

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59827-59850, 2024

Optimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers

Paulo Luza Alves, André Hochuli, Luiz Eduardo de Oliveira, Paulo Lisboa de Almeida

Comments Accepted for presentation at the International Conference on Machine Learning and Applications (ICMLA) 2024

Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning

Sajad Khodadadian, Pranay Sharma, Gauri Joshi, Siva Theja Maguluri

Comments 80 pages, 0 figure, accepted to ICML 2022 for long presentation

SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery

Enneng Yang, Li Shen, Zhenyi Wang, Guibing Guo, Xingwei Wang, Xiaocun Cao, Jie Zhang, Dacheng Tao

Comments This paper is an extended version of our previous work [arXiv:2402.02705] presented at ICML 2024

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

Charlie Hou, Akshat Shrivastava, Hongyuan Zhan, Rylan Conway, Trang Le, Adithya Sagar, Giulia Fanti, Daniel Lazar

Comments ICML 2024 (Oral). Latest revision corrects a discussion on concurrent work arXiv:2403.01749. We described their work as reliant on using closed-sourced models when in reality they also evaluate and use open source models. This has been corrected in this version

A new computationally efficient algorithm to solve Feature Selection for Functional Data Classification in high-dimensional spaces

Tobia Boschi, Francesca Bonin, Rodrigo Ordonez-Hurtado, Alessandra Pascale, Jonathan Epperlein

Journal ref ICML 2024: https://openreview.net/forum?id=a7MW5kFFOf

AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines

Renjith Prasad, Chathurangi Shyalika, Ramtin Zand, Fadi El Kalach, Revathy Venkataramanan, Ramy Harik, Amit Sheth

Comments 8 Pages, 6 Figures, 4 Tables, Predictive Models in Engineering Applications special session (MLPMEA )at International Conference on Machine Learning and Applications (ICMLA) 2024

Journal ref Predictive Models in Engineering Applications special session (MLPMEA) at International Conference on Machine Learning and Applications (ICMLA) 2024

Diffusion Language Models Are Versatile Protein Learners

Xinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, Quanquan Gu

Comments ICML 2024 camera-ready version

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

Rui Yang, Xiaoman Pan, Feng Luo, Shuang Qiu, Han Zhong, Dong Yu, Jianshu Chen

Comments Accepted by ICML 2024

PASOA- PArticle baSed Bayesian Optimal Adaptive design

Jacopo Iollo, Christophe Heinkelé, Pierre Alliez, Florence Forbes

Comments ICML 2024

Journal ref Proceedings of the 41st International Conference on Machine Learning, 2024

Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples

Thomas T. Zhang, Bruce D. Lee, Ingvar Ziemann, George J. Pappas, Nikolai Matni

Comments Appeared at ICML 2024

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback

Kihyun Kim, Jiawei Zhang, Asuman Ozdaglar, Pablo A. Parrilo

Comments ICML 2024

Sliding down the stairs: how correlated latent variables accelerate learning with neural networks

Lorenzo Bardone, Sebastian Goldt

Journal ref ICML 2024, PMLR 235:3024-3045

RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation

Jiawei Zhou, Linye Lyu, Daojing He, Yu Li

Comments 12 pages. In Proceedings of the Forty-first International Conference on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024

Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning

Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang

Comments ICML 2024 (oral)

Interpolated-MLPs: Controllable Inductive Bias

Sean Wu, Jordan Hong, Keyu Bai, Gregor Bachmann

Comments 13 pages, 3 figures, ICML HiLD 2024 Workshop: 2nd Workshop on High-dimensional Learning Dynamics

ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections

Massimo Bini, Karsten Roth, Zeynep Akata, Anna Khoreva

Comments Accepted to ICML 2024. Code available at https://github.com/mwbini/ether

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Wei Wang, Takashi Ishida, Yu-Jie Zhang, Gang Niu, Masashi Sugiyama

Comments ICML 2024

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu, Yi Wu

Comments 16 pages, 2 figures, 14 tables

Journal ref ICML 2024

MOMENT: A Family of Open Time-series Foundation Models

Mononito Goswami, Konrad Szafer, Arjun Choudhry, Yifu Cai, Shuo Li, Artur Dubrawski

Comments Accepted at ICML'24. This is a revision. See changelog in the Appendix

Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function

Elissa Mhanna, Mohamad Assaad

Comments In this version, we slightly modify the proof of Theorem 3.7 in the original publication. We remove the expectation in the proof that was added by error. The original publication can be found at: https://proceedings.mlr.press/v202/mhanna23a.html

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24701-24719, 2023

Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks

Stefano Sarao Mannelli, Yaraslau Ivashynka, Andrew Saxe, Luca Saglietti

Comments Accepted to ICML 2024

Balanced Resonate-and-Fire Neurons

Saya Higuchi, Sebastian Kairat, Sander M. Bohte, Sebastian Otte

Comments Accepted at ICML 2024, https://proceedings.mlr.press/v235/higuchi24a.html

Graph Neural Networks with a Distribution of Parametrized Graphs

See Hian Lee, Feng Ji, Kelin Xia, Wee Peng Tay

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26640-26660, 2024

Generative Marginalization Models

Sulin Liu, Peter J. Ramadge, Ryan P. Adams

Comments ICML 2024

Progressive-Hint Prompting Improves Reasoning in Large Language Models

Chuanyang Zheng, Zhengying Liu, Enze Xie, Zhenguo Li, Yu Li

Comments Accepted to ICML AI4MATH 2024

TabDDPM: Modelling Tabular Data with Diffusion Models

Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev, Artem Babenko

Comments code https://github.com/yandex-research/tab-ddpm

Journal ref Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023

Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective

Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Alireza Makhzani

Comments A long version of the ICML 2024 paper. Updated the caption of Fig 4 to emphasize the importance of the scale invariance of root-free methods

Exploring the Benefit of Activation Sparsity in Pre-training

Zhengyan Zhang, Chaojun Xiao, Qiujieli Qin, Yankai Lin, Zhiyuan Zeng, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou

Comments ICML 2024