ICML

Automating lichen monitoring in ecological studies using instance segmentation of time-lapse images

Safwen Naimi, Olfa Koubaa, Wassim Bouachir, Guillaume-Alexandre Bilodeau, Gregory Jeddore, Patricia Baines, David Correia, Andre Arsenault

Comments 6 pages, 3 Figures, 8 Tables, Accepted for publication in IEEE International Conference on Machine Learning and Applications (ICMLA), copyright IEEE

HCT: Hybrid Convnet-Transformer for Parkinson's disease detection and severity prediction from gait

Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau

Comments 6 pages, 6 figures, 3 tables, Accepted for publication in IEEE International Conference on Machine Learning and Applications (ICMLA), copyright IEEE

Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making

Axel Abels, Tom Lenaerts, Vito Trianni, Ann Nowé

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

Interpretable Alzheimer's Disease Classification Via a Contrastive Diffusion Autoencoder

Ayodeji Ijishakin, Ahmed Abdulaal, Adamos Hadjivasiliou, Sophie Martin, James Cole

Journal ref ICML (2023), 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH)

ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval

Kexun Zhang, Xianjun Yang, William Yang Wang, Lei Li

Comments ICML 2023

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

Sang Michael Xie, Tengyu Ma, Percy Liang

Comments ICML 2021 Long talk

UI Layout Generation with LLMs Guided by UI Grammar

Yuwen Lu, Ziang Tong, Qinyi Zhao, Chengzhi Zhang, Toby Jia-Jun Li

Comments ICML 2023 Workshop on AI and HCI

SimBIG: Field-level Simulation-Based Inference of Galaxy Clustering

Pablo Lemos, Liam Parker, ChangHoon Hahn, Shirley Ho, Michael Eickenberg, Jiamin Hou, Elena Massara, Chirag Modi, Azadeh Moradinezhad Dizgah, Bruno Regaldo-Saint Blancard, David Spergel

Comments 14 pages, 4 figures. A previous version of the paper was published in the ICML 2023 Workshop on Machine Learning for Astrophysics

Conformal Prediction for Federated Uncertainty Quantification Under Label Shift

Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii, Eric Moulines, Maxim Panov

Comments ICML 2023

Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation

Hayata Yamasaki, Sathyawageeswar Subramanian, Satoshi Hayakawa, Sho Sonoda

Comments 27 pages, 4 figures

Journal ref Proceedings of the 40th International Conference on Machine Learning (ICML2023) https://proceedings.mlr.press/v202/yamasaki23a.html

Inferring Relational Potentials in Interacting Systems

Armand Comas-Massagué, Yilun Du, Christian Fernandez, Sandesh Ghimire, Mario Sznaier, Joshua B. Tenenbaum, Octavia Camps

Comments Published at ICML 2023 (Oral)

Exponential weight averaging as damped harmonic motion

Jonathan Patsenker, Henry Li, Yuval Kluger

Comments 10 pages, 7 figures. ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems. 2023

Ego-perspective enhanced fitness training experience of AR Try to Move game

Chongyu Zhang

Comments 6 pages, 2 figures, 2 tables, 2023 International Conference on Machine Learning and Automation (CONF-MLA 2023)

Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction

Daniel Haider, Martin Ehler, Peter Balazs

Comments 10 pages main paper + 2 pages appendix, 4 figures, 2 algorithms, conference

Journal ref International Conference on Machine Learning 2023

E(n) Equivariant Message Passing Simplicial Networks

Floor Eijkelboom, Rob Hesselink, Erik Bekkers

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9071-9081, 2023

Learning Physical Models that Can Respect Conservation Laws

Derek Hansen, Danielle C. Maddix, Shima Alizadeh, Gaurav Gupta, Michael W. Mahoney

Comments ICML 2023, Physica D: Nonlinear Phenomena, Accepted

Journal ref Physica D: Nonlinear Phenomena, 457 (2024) 133952

Doubly Adversarial Federated Bandits

Jialin Yi, Milan Vojnović

Comments Published in ICML 2023 https://proceedings.mlr.press/v202/yi23a.html

Journal ref Proceedings of the 40th International Conference on Machine Learning 2023

Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption

Vasilii Feofanov, Malik Tiomoko, Aladin Virmaux

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10008-10033, 2023

Learning Recurrent Models with Temporally Local Rules

Azwar Abdulsalam, Joseph G. Makin

Comments Presented at the "Localized Learning" workshop at the International Conference on Machine Learning (ICML), July 2023. 6 pages, 5 figures, 2 tables

Exact Inference in High-order Structured Prediction

Chuyang Ke, Jean Honorio

Journal ref International Conference on Machine Learning (ICML), 2023

Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation

Anwar Said, Mudassir Shabbir, Tyler Derr, Waseem Abbas, Xenofon Koutsoukos

Comments 22nd IEEE International Conference on Machine Learning and Applications 2023

Revisiting Bellman Errors for Offline Model Selection

Joshua P. Zitovsky, Daniel de Marchi, Rishabh Agarwal, Michael R. Kosorok

Comments Published in ICML 2023

Journal ref In ICML (pp. 43369-43406). PMLR (2023)

Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work

Khawar Islam

Comments Added AAAI 2022 methods and working on ICLR 2022 methods and ICML 2022

A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization

Renzhe Xu, Xingxuan Zhang, Zheyan Shen, Tong Zhang, Peng Cui

Comments ICML 2022

Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)

Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Brauner, Yarin Gal

Journal ref ICML 2021 Workshop on Subset Selection in Machine Learning

On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions

Christopher Diehl, Tobias Klosek, Martin Krüger, Nils Murzyn, Torsten Bertram

Comments International Conference on Machine Learning, Workshop on New Frontiers in Learning, Control, and Dynamical Systems (ICML 2023 Frontiers4LCD); added further related work in Energy-based Model sections in V2

DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference

Wanrong Zhang, Ruqi Zhang

Journal ref published at ICML 2023

A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback

Guanyu Nie, Yididiya Y Nadew, Yanhui Zhu, Vaneet Aggarwal, Christopher John Quinn

Comments This extends the framework in previous version to adapt randomized offline approximation algorithms

Journal ref Proceedings of the 40th International Conference on Machine Learning, 2023

Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning

Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng

Comments 24 pages, 16 figures

Journal ref The Fortieth International Conference on Machine Learning (ICML2023)

Multi-spectral Entropy Constrained Neural Compression of Solar Imagery

Ali Zafari, Atefeh Khoshkhahtinat, Piyush M. Mehta, Nasser M. Nasrabadi, Barbara J. Thompson, Michael S. F. Kirk, Daniel da Silva

Comments Accepted to IEEE 22$^{nd}$ International Conference on Machine Learning and Applications 2023 (ICMLA)