ICML

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Yash Chandak, Shantanu Thakoor, Zhaohan Daniel Guo, Yunhao Tang, Remi Munos, Will Dabney, Diana L Borsa

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

Bayesian Model Selection, the Marginal Likelihood, and Generalization

Sanae Lotfi, Pavel Izmailov, Gregory Benton, Micah Goldblum, Andrew Gordon Wilson

Comments Extended version. Shorter ICML version available at arXiv:2202.11678v2

Poisoning Language Models During Instruction Tuning

Alexander Wan, Eric Wallace, Sheng Shen, Dan Klein

Comments ICML 2023

Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal

Naresh Kumar Gurulingan, Bahram Zonooz, Elahe Arani

Comments Accepted at 40th International Conference on Machine Learning (ICML)

DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning

Zifeng Wang, Zheng Zhan, Yifan Gong, Yucai Shao, Stratis Ioannidis, Yanzhi Wang, Jennifer Dy

Comments Accepted at ICML 2023 as a conference paper

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

Edresson Casanova, Julian Weber, Christopher Shulby, Arnaldo Candido Junior, Eren Gölge, Moacir Antonelli Ponti

Comments An Erratum was added on the last page of this paper

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:2709-2720, 2022

POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models

Korawat Tanwisuth, Shujian Zhang, Huangjie Zheng, Pengcheng He, Mingyuan Zhou

Comments ICML 2023; PyTorch code is available at https://github.com/korawat-tanwisuth/POUF

A Coupled Flow Approach to Imitation Learning

Gideon Freund, Elad Sarafian, Sarit Kraus

Comments Accepted at ICML 2023

Data-Driven Subgroup Identification for Linear Regression

Zachary Izzo, Ruishan Liu, James Zou

Comments Accepted at ICML 2023

R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents

Daniel D. Johnson, Daniel Tarlow, Christian Walder

Comments To appear at ICML 2023. 9 pages, 6 figures

Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes

Amir Hossein Saberi, Amir Najafi, Seyed Abolfazl Motahari, Babak H. Khalaj

Comments Accepted for ICML 2023; 27 pages

End-to-End Multi-Object Detection with a Regularized Mixture Model

Jaeyoung Yoo, Hojun Lee, Seunghyeon Seo, Inseop Chung, Nojun Kwak

Comments Accepted at ICML 2023

Distance Weighted Supervised Learning for Offline Interaction Data

Joey Hejna, Jensen Gao, Dorsa Sadigh

Comments ICML 2023

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

Zhaoyan Liu, Noel Vouitsis, Satya Krishna Gorti, Jimmy Ba, Gabriel Loaiza-Ganem

Comments Accepted at ICML 2023

Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling

Kolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi, Hannaneh Hajishirzi, Sameer Singh, Roy Fox

Comments in proceedings of ICML 23

Are Equivariant Equilibrium Approximators Beneficial?

Zhijian Duan, Yunxuan Ma, Xiaotie Deng

Comments To appear in ICML 2023

GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency

Min-seop Kwak, Jiuhn Song, Seungryong Kim

Comments ICML 2023

Cell-Free Latent Go-Explore

Quentin Gallouédec, Emmanuel Dellandréa

Comments Proceedings of the International Conference on Machine Learning, 2023

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

Peter J. Bevan, Amir Atapour-Abarghouei

Comments 9 pages, ICML 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:1874-1892, 2022

Fundamental Tradeoffs in Learning with Prior Information

Anirudha Majumdar

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

FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems

Matthieu Blanke, Marc Lelarge

Comments Accepted at ICML 2023

Multi-agent Online Scheduling: MMS Allocations for Indivisible Items

Shengwei Zhou, Rufan Bai, Xiaowei Wu

Comments 29 pages, 1 figure (to appear in ICML 2023)

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

Jihye Kim, Aristide Baratin, Yan Zhang, Simon Lacoste-Julien

Comments Accepted to ICML 2023

Certifying Ensembles: A General Certification Theory with S-Lipschitzness

Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi

Comments Accepted to ICML 2023

Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control

Zhen Lin, Shubhendu Trivedi, Cao Xiao, Jimeng Sun

Comments Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023. 11 pages (main paper, including references) + 10 pages (supplementary material)

Efficient Training of Deep Equilibrium Models

Bac Nguyen, Lukas Mauch

Comments ICML 2022 Workshop

Communication-Efficient Adaptive Federated Learning

Yujia Wang, Lu Lin, Jinghui Chen

Comments Updated version. A previous version is accepted by ICML 2022 (37 pages, 7 figures, 3 tables)

Feature Learning and Signal Propagation in Deep Neural Networks

Yizhang Lou, Chris Mingard, Yoonsoo Nam, Soufiane Hayou

Comments 35 pages

Journal ref International Conference on Machine Learning. PMLR, 2022

Online Active Learning for Soft Sensor Development using Semi-Supervised Autoencoders

Davide Cacciarelli, Murat Kulahci, John Tyssedal

Comments ICML 2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World

Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity

Matthew Fahrbach, Vahab Mirrokni, Morteza Zadimoghaddam

Comments 19 pages, 8 figures. This version fixes a bug in the threshold sampling algorithm that implicitly assumed monotonicity. All original results hold

Journal ref Proceedings of the 36th International Conference on Machine Learning (ICML 2019) 1833-1842