ICML

A Theoretical Analysis of the Learning Dynamics under Class Imbalance

Emanuele Francazi, Marco Baity-Jesi, Aurelien Lucchi

Comments In the latest update of our paper, we've refined the formulations of the theorems and their proofs in the appendix to improve clarity

Journal ref International Conference on Machine Learning 2023, (PMLR) 10285-10322

Deletion Robust Submodular Maximization over Matroids

Paul Dütting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Morteza Zadimoghaddam

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:5671-5693, 2022

Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity

Georgios Amanatidis, Federico Fusco, Philip Lazos, Stefano Leonardi, Alberto Marchetti Spaccamela, Rebecca Reiffenhäuser

Comments This version addresses a gap in the probabilistic analysis of the approximation guarantees in the previous version of this work. We provide a simple fix via a standard sampling routine while maintaining the same approximation guarantees and complexity bounds. (formerly appeared as arXiv:2007.05014v2 in error)

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:231-242, 2021

When Explanations Lie: Why Many Modified BP Attributions Fail

Leon Sixt, Maximilian Granz, Tim Landgraf

Comments Published in ICML 2020 - Updated Proof

Hieros: Hierarchical Imagination on Structured State Space Sequence World Models

Paul Mattes, Rainer Schlosser, Ralf Herbrich

Comments Submitted to ICML 2024, 23 pages, 11 figures, code available at: https://github.com/Snagnar/Hieros

Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization

Xiang Gao, Yuqi Zhang, Yingjie Tian

Comments Proceedings of the 39th International Conference on Machine Learning (ICML), PMLR 162:7183-7207, 2022

Journal ref International Conference on Machine Learning (ICML). PMLR 162, 2022, 7183-7207

Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path

Qiwei Di, Jiafan He, Dongruo Zhou, Quanquan Gu

Comments 28 pages, 1 figure, In ICML 2023

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs

Junkai Zhang, Weitong Zhang, Quanquan Gu

Comments 37 pages, 1 figure, 2 tables. In ICML 2023

On the Statistical Benefits of Temporal Difference Learning

David Cheikhi, Daniel Russo

Comments 26 pages, 7 figures, submitted to ICML 2023

One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill

Sangwoo Shin, Daehee Lee, Minjong Yoo, Woo Kyung Kim, Honguk Woo

Comments ICML-2023 Camera Ready Version

Slot-VAE: Object-Centric Scene Generation with Slot Attention

Yanbo Wang, Letao Liu, Justin Dauwels

Comments ICML 2023 https://proceedings.mlr.press/v202/wang23r.html

Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes

Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang

Comments We study the corruption-robust MDPs and contextual bandits with general function approximation

Journal ref ICML 2023

Optimal Shrinkage for Distributed Second-Order Optimization

Fangzhao Zhang, Mert Pilanci

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41523-41549, 2023

Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network

Yuri Kinoshita, Kenta Oono, Kenji Fukumizu, Yuichi Yoshida, Shin-ichi Maeda

Comments accepted to ICML 2023, some notations adjusted from the submitted version

Deep Continuous Networks

Nergis Tomen, Silvia L. Pintea, Jan C. van Gemert

Comments Presented at ICML 2021

Journal ref In International Conference on Machine Learning 2021 Jul 1 (pp. 10324-10335). PMLR

Explainable AI for survival analysis: a median-SHAP approach

Lucile Ter-Minassian, Sahra Ghalebikesabi, Karla Diaz-Ordaz, Chris Holmes

Comments Accepted to the Interpretable Machine Learning for Healthcare (IMLH) workshop of the ICML 2022 Conference

On the Generalizability of ECG-based Stress Detection Models

Pooja Prajod, Elisabeth André

Comments Published in Proceedings of 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)

Circuit Breaking: Removing Model Behaviors with Targeted Ablation

Maximilian Li, Xander Davies, Max Nadeau

Journal ref Workshop on Challenges in Deployable Generative AI at International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA. 2023

Particle Transformer for Jet Tagging

Huilin Qu, Congqiao Li, Sitian Qian

Comments 12 pages, 3 figures. Accepted to the 39th International Conference on Machine Learning (ICML), 2022. v3: fixed a typo on the interaction matrix dimensionality in Sec. 4

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:18281-18292, 2022

Self-Repellent Random Walks on General Graphs -- Achieving Minimal Sampling Variance via Nonlinear Markov Chains

Vishwaraj Doshi, Jie Hu, Do Young Eun

Comments Selected for oral presentation at ICML 2023. Recipient of Outstanding Paper award

N$\text{A}^\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning

Zichuan Liu, Yuanyang Zhu, Chunlin Chen

Comments Accepted by International Conference on Machine Learning (ICML 2023)

Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline

Seonmin Koo, Chanjun Park, Jinsung Kim, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim

Comments Accepted for Data-centric Machine Learning Research (DMLR) Workshop at ICML 2023

The Manifold Scattering Transform for High-Dimensional Point Cloud Data

Joyce Chew, Holly R. Steach, Siddharth Viswanath, Hau-Tieng Wu, Matthew Hirn, Deanna Needell, Smita Krishnaswamy, Michael Perlmutter

Comments Accepted for publication in the TAG in DS Workshop at ICML. For subsequent theoretical guarantees, please see Section 6 of arXiv:2208.08561

Novel Representation Learning Technique using Graphs for Performance Analytics

Tarek Ramadan, Ankur Lahiry, Tanzima Z. Islam

Comments This paper has been accepted at 22nd International Conference on Machine Learning and Applications (ICMLA2023)

Optimal Sets and Solution Paths of ReLU Networks

Aaron Mishkin, Mert Pilanci

Comments Minor updates and corrections to clarify the role of merge/split symmetries in formation of ReLU optimal set and add missing sufficient conditions for all minimal models to have the same cardinality

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24888-24924, 2023

Hyperbolic Image-Text Representations

Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, Ramakrishna Vedantam

Comments ICML 2023 (v3: Add link to code in abstract)

Multiple Locally Linear Kernel Machines

David Picard

Comments This paper was written in 2014 and was originally submitted but rejected at ICML'15

Machine Learning-based xApp for Dynamic Resource Allocation in O-RAN Networks

Mohammed M. H. Qazzaz, Łukasz Kułacz, Adrian Kliks, Syed A. Zaidi, Marcin Dryjanski, Des McLernon

Comments 6 pages, 6 figures, 2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)

Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method

Liqiang Yu, Bo Liu, Qunwei Lin, Xinyu Zhao, Chang Che

Comments It accepted by The 6th International Conference on Machine Learning and Machine Intelligence (MLMI 2023)

DeepSweep: Parallel and Scalable Spectrum Sensing via Convolutional Neural Networks

Clifton Paul Robinson, Daniel Uvaydov, Salvatore D'Oro, Tommaso Melodia

Comments 6 pages, 9 figures, IEEE ICMLCN 2024 - IEEE International Conference on Machine Learning for Communication and Networking, Stockholm, Sweden, 2024