ICML

Distribution Free Prediction Sets for Node Classification

Jase Clarkson

Comments Appeared at ICML 2023

Reliability-Optimized User Admission Control for URLLC Traffic: A Neural Contextual Bandit Approach

Omid Semiari, Hosein Nikopour, Shilpa Talwar

Comments To be published in the proceedings of the 2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)

Evaluating Self-Supervised Learning via Risk Decomposition

Yann Dubois, Tatsunori Hashimoto, Percy Liang

Comments Oral at ICML 2023

Gaussian processes at the Helm(holtz): A more fluid model for ocean currents

Renato Berlinghieri, Brian L. Trippe, David R. Burt, Ryan Giordano, Kaushik Srinivasan, Tamay Özgökmen, Junfei Xia, Tamara Broderick

Comments 51 pages, 16 figures

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2113-2163, 2023

Sharper Bounds for $\ell_p$ Sensitivity Sampling

David P. Woodruff, Taisuke Yasuda

Comments To appear in ICML 2023; added discussion of prior work

Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective

Khanh Nguyen

Comments Proceedings of the First Workshop on Theory of Mind in Communicating Agents at (TOM @ ICML 2023)

Transfer Learning for Causal Effect Estimation

Song Wei, Hanyu Zhang, Ronald Moore, Rishikesan Kamaleswaran, Yao Xie

Comments Preliminary version, titled "Transfer causal learning: Causal effect estimation with knowledge transfer", has been presented in ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH), 2023; see the arXiv version in v2

Online Algorithmic Recourse by Collective Action

Elliot Creager, Richard Zemel

Comments Appeared in the ICML 2021 Workshop on Algorithmic Recourse

Distributional Offline Policy Evaluation with Predictive Error Guarantees

Runzhe Wu, Masatoshi Uehara, Wen Sun

Comments Accepted at ICML 2023

Explainability as statistical inference

Hugo Henri Joseph Senetaire, Damien Garreau, Jes Frellsen, Pierre-Alexandre Mattei

Comments 10 pages, 22 figures, published at ICLR 2023

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30584-30612, 2023

Continual Learning via Sequential Function-Space Variational Inference

Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal

Comments Published in Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

Function-Space Regularization in Neural Networks: A Probabilistic Perspective

Tim G. J. Rudner, Sanyam Kapoor, Shikai Qiu, Andrew Gordon Wilson

Comments Published in Proceedings of the 40th International Conference on Machine Learning (ICML 2023)

Designing Discontinuities

Ibtihal Ferwana, Suyoung Park, Ting-Yi Wu, Lav R. Varshney

Comments A short version is accepted in Neural Compression ICML Worksop July 19th, 2023

How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control

Jacopo Teneggi, Matthew Tivnan, J. Webster Stayman, Jeremias Sulam

Journal ref International Conference on Machine Learning (2023)

Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability

Thomy Phan, Fabian Ritz, Philipp Altmann, Maximilian Zorn, Jonas Nüßlein, Michael Kölle, Thomas Gabor, Claudia Linnhoff-Popien

Comments Accepted to ICML 2023

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

Guy Hacohen, Avihu Dekel, Daphna Weinshall

Comments ICML 2022

Journal ref 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets

Guy Hacohen, Leshem Choshen, Daphna Weinshall

Comments Published at ICML 2020

Journal ref Proceedings: 37th International Conference on Machine Learning (ICML), Viena Austria, July 2020

Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks

Daphna Weinshall, Gad Cohen, Dan Amir

Comments ICML 2018

Journal ref Proceedings: 35th International Conference on Machine Learning (ICML), oral, Stockholm Sweden, July 2018

Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks

Yijia Weng, Kaichun Mo, Ruoxi Shi, Yanchao Yang, Leonidas J. Guibas

Comments ICML 2023. Project page: https://yijiaweng.github.io/geo-eigen-length

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36958-36977, 2023

Private Statistical Estimation of Many Quantiles

Clément Lalanne, Aurélien Garivier, Rémi Gribonval

Journal ref ICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honolulu, United States

Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees

Haotian Ju, Dongyue Li, Hongyang R. Zhang

Comments 38 pages. Appeared in ICML 2022

nbi: the Astronomer's Package for Neural Posterior Estimation

Keming Zhang, Joshua S. Bloom, Stéfan van der Walt, Nina Hernitschek

Comments Update references. Accepted to NeurIPS 2023 Workshop on Deep Learning and Inverse Problems. Initially appeared at ICML 2023 Workshop on Machine Learning for Astrophysics. Code at https://github.com/kmzzhang/nbi

The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models

Tolga Ergen, Mert Pilanci

Comments A preliminary version of part of this work was published at ICML 2020 with the title "Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks"

Fair and Robust Estimation of Heterogeneous Treatment Effects for Policy Learning

Kwangho Kim, José R. Zubizarreta

Journal ref Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 16997--17014, 2023

In-Context Exemplars as Clues to Retrieving from Large Associative Memory

Jiachen Zhao

Comments Presented at Neural Conversational AI @ ICML 2023 and Associative Memory & Hopfield Networks @ NeurIPS 2023

Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal

Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra, Simone Calderara, Andrea Passerini, Stefano Teso

Comments 40th International Conference on Machine Learning (ICML 2023)

A Comprehensive Python Library for Deep Learning-Based Event Detection in Multivariate Time Series Data and Information Retrieval in NLP

Menouar Azib, Benjamin Renard, Philippe Garnier, Vincent Génot, Nicolas André

Comments 2023 International Conference on Machine Learning and Applications (ICMLA)

GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations

Dan Ley, Saumitra Mishra, Daniele Magazzeni

Comments Published as a conference paper at ICML 2023 (9 page main text, 3 page references, 16 page appendix)

ClimaX: A foundation model for weather and climate

Tung Nguyen, Johannes Brandstetter, Ashish Kapoor, Jayesh K. Gupta, Aditya Grover

Comments International Conference on Machine Learning 2023

The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation

Philip Amortila, Nan Jiang, Csaba Szepesvári

Comments Accepted to ICML 2023. The arXiv version contains improved results