ICML

On the Role of Attention in Prompt-tuning

Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis

Comments Published at ICML 2023

Boosting Offline Reinforcement Learning with Action Preference Query

Qisen Yang, Shenzhi Wang, Matthieu Gaetan Lin, Shiji Song, Gao Huang

Comments International Conference on Machine Learning 2023

Under-Counted Tensor Completion with Neural Incorporation of Attributes

Shahana Ibrahim, Xiao Fu, Rebecca Hutchinson, Eugene Seo

Comments 33 pages, 5 figures, ICML 2023

Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models

Alexander Lin, Bahareh Tolooshams, Yves Atchadé, Demba Ba

Comments 29 pages, 4 figures

Journal ref International Conference on Machine Learning, 2023

Structural Re-weighting Improves Graph Domain Adaptation

Shikun Liu, Tianchun Li, Yongbin Feng, Nhan Tran, Han Zhao, Qiu Qiang, Pan Li

Comments ICML 2023, Codes: https://github.com/Graph-COM/StruRW

End-to-end Differentiable Clustering with Associative Memories

Bishwajit Saha, Dmitry Krotov, Mohammed J. Zaki, Parikshit Ram

Comments Accepted to ICML 2023

Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning

Sam Lobel, Akhil Bagaria, George Konidaris

Comments 11 pages (+9 appendix). Published as a conference paper at ICML 2023. Code available at https://github.com/samlobel/CFN/

Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning

Mattia Atzeni, Mrinmaya Sachan, Andreas Loukas

Comments Accepted for publication at the International Conference on Machine Learning, ICML 2023

Nonparametric Iterative Machine Teaching

Chen Zhang, Xiaofeng Cao, Weiyang Liu, Ivor Tsang, James Kwok

Comments ICML 2023 (20 pages, 10 figures)

Provable Dynamic Fusion for Low-Quality Multimodal Data

Qingyang Zhang, Haitao Wu, Changqing Zhang, Qinghua Hu, Huazhu Fu, Joey Tianyi Zhou, Xi Peng

Comments Accepted by ICML 2023

Provable Benefit of Mixup for Finding Optimal Decision Boundaries

Junsoo Oh, Chulhee Yun

Comments ICML 2023 camera-ready version; 48 pages

Fisher Information Embedding for Node and Graph Learning

Dexiong Chen, Paolo Pellizzoni, Karsten Borgwardt

Comments ICML 2023

Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts

Étienne Marcotte, Valentina Zantedeschi, Alexandre Drouin, Nicolas Chapados

Comments 47 pages, 37 figures, camera-ready version, Fortieth International Conference on Machine Learning (ICML 2023)

Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning

Nader Asadi, MohammadReza Davari, Sudhir Mudur, Rahaf Aljundi, Eugene Belilovsky

Comments Accepted at ICML 2023

Fast Rates for Maximum Entropy Exploration

Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Remi Munos, Alexey Naumov, Pierre Perrault, Yunhao Tang, Michal Valko, Pierre Menard

Comments ICML-2023

Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks

Yiwei Lu, Gautam Kamath, Yaoliang Yu

Comments Accepted to ICML 2023

In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation

Alicia Curth, Mihaela van der Schaar

Comments To appear in the Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023

Large Language Models Can Be Easily Distracted by Irrelevant Context

Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed Chi, Nathanael Schärli, Denny Zhou

Comments Published in ICML 2023

On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters

Wonyeol Lee, Sejun Park, Alex Aiken

Comments To appear at ICML 2023

Direct Parameterization of Lipschitz-Bounded Deep Networks

Ruigang Wang, Ian R. Manchester

Comments accepted to ICML 2023

Retrieval-Augmented Multimodal Language Modeling

Michihiro Yasunaga, Armen Aghajanyan, Weijia Shi, Rich James, Jure Leskovec, Percy Liang, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih

Comments Published at ICML 2023. Blog post available at https://cs.stanford.edu/~myasu/blog/racm3/

When is Realizability Sufficient for Off-Policy Reinforcement Learning?

Andrea Zanette

Comments Appears in ICML 2023 - any feedback is welcome

"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts

Haoran Zhang, Harvineet Singh, Marzyeh Ghassemi, Shalmali Joshi

Comments Published in ICML 2023

A Kernel-Based View of Language Model Fine-Tuning

Sadhika Malladi, Alexander Wettig, Dingli Yu, Danqi Chen, Sanjeev Arora

Comments Accepted at ICML 2023. Code and pre-computed kernels are publicly available at https://github.com/princeton-nlp/LM-Kernel-FT

Less is More: Task-aware Layer-wise Distillation for Language Model Compression

Chen Liang, Simiao Zuo, Qingru Zhang, Pengcheng He, Weizhu Chen, Tuo Zhao

Comments Proceedings of ICML 2023

Entropy-driven Unsupervised Keypoint Representation Learning in Videos

Ali Younes, Simone Schaub-Meyer, Georgia Chalvatzaki

Comments 29 pages, 14 figures, Accepted at ICML 2023

Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction

Jianyi Zhang, Ang Li, Minxue Tang, Jingwei Sun, Xiang Chen, Fan Zhang, Changyou Chen, Yiran Chen, Hai Li

Comments ICML 2023

Beyond Uniform Lipschitz Condition in Differentially Private Optimization

Rudrajit Das, Satyen Kale, Zheng Xu, Tong Zhang, Sujay Sanghavi

Comments To appear in ICML 2023

Global Context Vision Transformers

Ali Hatamizadeh, Hongxu Yin, Greg Heinrich, Jan Kautz, Pavlo Molchanov

Comments Accepted to ICML 2023

Learning Intuitive Policies Using Action Features

Mingwei Ma, Jizhou Liu, Samuel Sokota, Max Kleiman-Weiner, Jakob Foerster

Comments ICML 2023