ICML

Leveraging Contextual Counterfactuals Toward Belief Calibration

Qiuyi, Zhang, Michael S. Lee, Sherol Chen

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

Closing the stellar labels gap: An unsupervised, generative model for $\textit{Gaia}$ BP/RP spectra

Alexander Laroche, Joshua S. Speagle

Comments Accepted at the ICML 2023 Workshop on Machine Learning for Astrophysics. 6 pages, 3 figures

Journal ref ICML 2023 Workshop on Machine Learning for Astrophysics

Regret-Minimizing Double Oracle for Extensive-Form Games

Xiaohang Tang, Le Cong Dinh, Stephen Marcus McAleer, Yaodong Yang

Comments Accepted at ICML, 2023

Adversarial Policies Beat Superhuman Go AIs

Tony T. Wang, Adam Gleave, Tom Tseng, Kellin Pelrine, Nora Belrose, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell

Comments Accepted to ICML 2023, see paper for changelog

A kernel Stein test of goodness of fit for sequential models

Jerome Baum, Heishiro Kanagawa, Arthur Gretton

Comments 18 pages. Accepted to ICML 2023

Adapting to Mixing Time in Stochastic Optimization with Markovian Data

Ron Dorfman, Kfir Y. Levy

Comments ICML 2022

Exposing the Fake: Effective Diffusion-Generated Images Detection

Ruipeng Ma, Jinhao Duan, Fei Kong, Xiaoshuang Shi, Kaidi Xu

Comments AdvML-Frontiers@ICML 2023

Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

Shantanu Ghosh, Ke Yu, Forough Arabshahi, Kayhan Batmanghelich

Comments appeared as v5 of arXiv:2302.10289 which was replaced in error, which drifted into a different work, accepted in ICML 2023

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11360-11397, 2023

From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning

Edwige Cyffers, Aurélien Bellet, Debabrota Basu

Comments Accepted to ICML 2023. v3: added references to the first papers that introduced block-wise fixed-point iterations (Iutzeler et al., 2013; Bianchi et al., 2016)

spred: Solving $L_1$ Penalty with SGD

Liu Ziyin, Zihao Wang

Comments ICML 2023, 16 pages, 10 figures, and 2 tables

Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models

Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee

Comments 17 pages, 13 figures, ICML 2023 Workshop on Challenges in Deployable Generative AI

Differentiable Forward Projector for X-ray Computed Tomography

Hyojin Kim, Kyle Champley

Comments ICML 2023 Workshop: Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators

Neural Polytopes

Koji Hashimoto, Tomoya Naito, Hisashi Naito

Comments 5 pages, 9 figures. v2: References added. Accepted at the 1st Workshop on the Synergy of Scientific and Machine Learning Modeling at International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA. 2023

Conformalization of Sparse Generalized Linear Models

Etash Kumar Guha, Eugene Ndiaye, Xiaoming Huo

Comments ICML 2023

Estimating label quality and errors in semantic segmentation data via any model

Vedang Lad, Jonas Mueller

Comments ICML Workshop on Data-centric Machine Learning Research 2023

Physics-constrained Random Forests for Turbulence Model Uncertainty Estimation

Marcel Matha, Christian Morsbach

Comments Workshop on Synergy of Scientific and Machine Learning Modeling, SynS & ML ICML

Quantum Policy Gradient Algorithm with Optimized Action Decoding

Nico Meyer, Daniel D. Scherer, Axel Plinge, Christopher Mutschler, Michael J. Hartmann

Comments Accepted to the 40th International Conference on Machine Learning (ICML 2023), Honolulu, Hawaii, USA. 22 pages, 10 figures, 3 tables

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24592-24613, 2023

Adversarial Cheap Talk

Chris Lu, Timon Willi, Alistair Letcher, Jakob Foerster

Comments To be published at ICML 2023. Project video and code are available at https://sites.google.com/view/adversarial-cheap-talk

Evaluating Summary Statistics with Mutual Information for Cosmological Inference

Ce Sui, Xiaosheng Zhao, Tao Jing, Yi Mao

Comments Accepted at the ICML 2023 Workshop on Machine Learning for Astrophysics, comments welcome

Multi-fidelity Emulator for Cosmological Large Scale 21 cm Lightcone Images: a Few-shot Transfer Learning Approach with GAN

Kangning Diao, Yi Mao

Comments Accepted at the ICML 2023 Workshop on Machine Learning for Astrophysics

Detecting Tidal Features using Self-Supervised Representation Learning

Alice Desmons, Sarah Brough, Francois Lanusse

Comments Accepted at the ICML 2023 Workshop on Machine Learning for Astrophysics

Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes

Justin Diamond, Markus Lill

Comments Published at ICML 2023 Workshop on Structured Probabilistic Inference and Generative Modeling

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

Zhun Yang, Joohyung Lee, Chiyoun Park

Comments 27 pages

Journal ref PMLR 162:25096-25122 (ICML 2022)

On the Challenges of Deploying Privacy-Preserving Synthetic Data in the Enterprise

Lauren Arthur, Jason Costello, Jonathan Hardy, Will O'Brien, James Rea, Gareth Rees, Georgi Ganev

Comments Accepted to the 1st Workshop on Challenges in Deployable Generative AI, part of ICML 2023

Robust Ranking Explanations

Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie

Comments Accepted to IMLH (Interpretable ML in Healthcare) workshop at ICML 2023. arXiv admin note: substantial text overlap with arXiv:2212.14106

Exploring Antitrust and Platform Power in Generative AI

Konrad Kollnig, Qian Li

Comments Accepted by the Workshop on Generative AI and Law (GenLaw '23) of ICML '23

(Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibility

Kacper Sokol, Julia E. Vogt

Comments Workshop on Interpretable ML in Healthcare at 2023 International Conference on Machine Learning (ICML)

Conformal Prediction with Large Language Models for Multi-Choice Question Answering

Bhawesh Kumar, Charlie Lu, Gauri Gupta, Anil Palepu, David Bellamy, Ramesh Raskar, Andrew Beam

Comments Updated sections on prompt engineering. Expanded sections 4.1 and 4.2 and appendix. Included additional references. Work published at the ICML 2023 (Neural Conversational AI TEACH) workshop

Synthetic data, real errors: how (not) to publish and use synthetic data

Boris van Breugel, Zhaozhi Qian, Mihaela van der Schaar

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

Conditional Graph Information Bottleneck for Molecular Relational Learning

Namkyeong Lee, Dongmin Hyun, Gyoung S. Na, Sungwon Kim, Junseok Lee, Chanyoung Park

Comments ICML 2023