ICML

A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks

Felix Grün, Christian Rupprecht, Nassir Navab, Federico Tombari

Journal ref 33rd International Conference on Machine Learning (ICML) Workshop on Visualization for Deep Learning, New York City, USA, 2016

Collaborative Heterogeneous Causal Inference Beyond Meta-analysis

Tianyu Guo, Sai Praneeth Karimireddy, Michael I. Jordan

Comments submitted to ICML

A Mathematical Model for Curriculum Learning for Parities

Elisabetta Cornacchia, Elchanan Mossel

Journal ref ICML 2023

Reinforcement Learning Approach for Integrating Compressed Contexts into Knowledge Graphs

Ngoc Quach, Qi Wang, Zijun Gao, Qifeng Sun, Bo Guan, Lillian Floyd

Comments This paper has been accepted by the 2024 International Conference on Machine Learning and Neural Networks (MLNN 2024)

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

Luke Marris, Paul Muller, Marc Lanctot, Karl Tuyls, Thore Graepel

Comments ICML 2021, 9 pages, coded implementation available in https://github.com/deepmind/open_spiel/ (jpsro.py in examples)

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

Shuang Qiu, Lingxiao Wang, Chenjia Bai, Zhuoran Yang, Zhaoran Wang

Comments ICML 2022

Approximate Stein Classes for Truncated Density Estimation

Daniel J. Williams, Song Liu

Comments Accepted to ICML 2023

Score Matching for Truncated Density Estimation on a Manifold

Daniel J. Williams, Song Liu

Comments 11 pages, 5 figures, accepted as a workshop entry to Topology, Algebra, and Geometry in Data Science (ICML workshop)

Efficient Duple Perturbation Robustness in Low-rank MDPs

Yang Hu, Haitong Ma, Bo Dai, Na Li

Comments 25 pages, 8 figures, in submission to ICML'24

Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space

Zhengdao Chen

Comments 65 pages, 3 figures. Published by the Journal of Machine Learning Research and presented partially at the 40th International Conference on Machine Learning (ICML 2023)

Journal ref Journal of Machine Learning Research, 25(109):1-65, 2024

SepVAE: a contrastive VAE to separate pathological patterns from healthy ones

Robin Louiset, Edouard Duchesnay, Antoine Grigis, Benoit Dufumier, Pietro Gori

Comments Workshop on Interpretable ML in Healthcare at International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA. 2023

Difference of Submodular Minimization via DC Programming

Marwa El Halabi, George Orfanides, Tim Hoheisel

Comments Removed minor errors in Proposition 2.7, Theorem 4.3 and Corollary 4.4. Key results unchanged (see Erratum on p.4). Also fixed typos

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

GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification

Ali Pesaranghader, Nikhil Verma, Manasa Bharadwaj

Comments 7 pages, 8 tables. Published in: 2023 International Conference on Machine Learning and Applications (ICMLA)

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

Louis Bethune, Paul Novello, Thibaut Boissin, Guillaume Coiffier, Mathieu Serrurier, Quentin Vincenot, Andres Troya-Galvis

Comments 27 pages, 11 figures, International Conference on Machine Learning 2023, (ICML 2023)

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han

Comments ICML 2023. First two authors contributed equally to this work

Neural Image Compression with Quantization Rectifier

Wei Luo, Bo Chen

Comments Published at International Conference on Machine Learning (ICML) Neural Compression Workshop 2023, Honolulu, Hawaii, USA. PMLR 202, 2023. Copyright 2023 by the authors

Omega: Optimistic EMA Gradients

Juan Ramirez, Rohan Sukumaran, Quentin Bertrand, Gauthier Gidel

Comments Oral at the LatinX in AI workshop @ ICML 2023

Bayesian Optimization that Limits Search Region to Lower Dimensions Utilizing Local GPR

Yasunori Taguchi, Hiro Gangi

Comments 8 pages, 13 figures, 22nd International Conference on Machine Learning and Applications (ICMLA2023)

Journal ref 2023 International Conference on Machine Learning and Applications (ICMLA), Jacksonville, FL, USA, 2023, pp. 202-209

Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure

Ryoma Sato

Comments ICML 2023

Block subsampled randomized Hadamard transform for low-rank approximation on distributed architectures

Oleg Balabanov, Matthias Beaupere, Laura Grigori, Victor Lederer

Journal ref Proceedings of the International Conference on Machine Learning, pp. 1564-1576. PMLR, 2023

Effective Structured Prompting by Meta-Learning and Representative Verbalizer

Weisen Jiang, Yu Zhang, James T. Kwok

Comments Accepted at ICML 2023

Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels

Fabian Altekrüger, Johannes Hertrich, Gabriele Steidl

Comments Accepted at ICML 2023

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:664-690, 2023

Detecting Relevant Information in High-Volume Chat Logs: Keyphrase Extraction for Grooming and Drug Dealing Forensic Analysis

Jeovane Honório Alves, Horácio A. C. G. Pedroso, Rafael Honorio Venetikides, Joel E. M. Köster, Luiz Rodrigo Grochocki, Cinthia O. A. Freitas, Jean Paul Barddal

Comments Accepted for presentation at the 22nd IEEE International Conference on Machine Learning and Applications (ICMLA) 2023

DADO -- Low-Cost Query Strategies for Deep Active Design Optimization

Jens Decke, Christian Gruhl, Lukas Rauch, Bernhard Sick

Journal ref 2023 International Conference on Machine Learning and Applications (ICMLA) p.1611-1618

Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise

Shiwei Zeng, Jie Shen

Comments ICML 2023. V2 fixed typos

Fairness Evaluation for Uplift Modeling in the Absence of Ground Truth

Serdar Kadioglu, Filip Michalsky

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

Deep Joint Source-Channel Coding Over Cooperative Relay Networks

Chenghong Bian, Yulin Shao, Haotian Wu, Deniz Gunduz

Comments Accepted to IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) 2024, code available via this link https://github.com/aprilbian/Relay_JSCC

Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning

Wu Lin, Valentin Duruisseaux, Melvin Leok, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

Comments A long version of the ICML 2023 paper. Updated the main text to emphasize challenges of using existing Riemannian methods to estimate sparse and structured SPD matrices

Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization

Sijia Chen, Yu-Jie Zhang, Wei-Wei Tu, Peng Zhao, Lijun Zhang

Comments v3 substantially improves the presentation and has a few improvements, including the regret bound for strongly convex functions; v2 is an extended version that enriches the content with improved regret bounds for strongly convex functions, discussions on the optimism design for dynamic regret minimization, and extensions to non-smooth scenarios; v1 is the ICML 2023 conference version

Local and Regional Counterfactual Rules: Summarized and Robust Recourses

Salim I. Amoukou, Nicolas J. B Brunel

Comments ICML (International Conference on Machine Learning) 2023 Workshop on Counterfactuals in Minds and Machines

Journal ref ICML (International Conference on Machine Learning) 2023 Workshop on Counterfactuals in Minds and Machines