ICML

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

Scott Fujimoto, David Meger, Doina Precup

Comments ICML 2021

Bigger, Better, Faster: Human-level Atari with human-level efficiency

Max Schwarzer, Johan Obando-Ceron, Aaron Courville, Marc Bellemare, Rishabh Agarwal, Pablo Samuel Castro

Comments ICML 2023, revised version

Tighter Bounds on the Expressivity of Transformer Encoders

David Chiang, Peter Cholak, Anand Pillay

Comments Presented at ICML 2023. Typo corrections in Appendix B and Section 8.1

Comprehending Lexical and Affective Ontologies in the Demographically Diverse Spatial Social Media Discourse

Salim Sazzed

Comments Accepted in 22nd IEEE International Conference on Machine Learning and Applications (ICMLA), 2023

What factors influence the popularity of user-generated text in the creative domain? A case study of book reviews

Salim Sazzed

Comments Accepted in 22nd IEEE International Conference on Machine Learning and Applications (ICMLA), 2023

Decentralized SGD and Average-direction SAM are Asymptotically Equivalent

Tongtian Zhu, Fengxiang He, Kaixuan Chen, Mingli Song, Dacheng Tao

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

Counterfactually Comparing Abstaining Classifiers

Yo Joong Choe, Aditya Gangrade, Aaditya Ramdas

Comments Accepted to NeurIPS 2023. Preliminary work presented at the ICML 2023 Workshop on Counterfactuals in Minds and Machines. Code available at https://github.com/yjchoe/ComparingAbstainingClassifiers

B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

Miruna Oprescu, Jacob Dorn, Marah Ghoummaid, Andrew Jesson, Nathan Kallus, Uri Shalit

Comments 20 pages, 4 figures, ICML 2023

Journal ref PMLR 202 (2023) 26599-26618

Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies

Ilyas Fatkhullin, Anas Barakat, Anastasia Kireeva, Niao He

Comments This work was initially submitted in October 2022

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9827-9869, 2023

Certified Data Removal from Machine Learning Models

Chuan Guo, Tom Goldstein, Awni Hannun, Laurens van der Maaten

Comments Accepted to ICML 2020

Federated Learning via Active RIS Assisted Over-the-Air Computation

Deyou Zhang, Ming Xiao, Mikael Skoglund, H. Vincent Poor

Comments This paper was submitted to the IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN), Stockholm, Sweden, 2024

Loss Balancing for Fair Supervised Learning

Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan

Comments This paper has been published in the Fortieth International Conference on Machine Learning (ICML 2023)

Equivariance Is Not All You Need: Characterizing the Utility of Equivariant Graph Neural Networks for Particle Physics Tasks

Savannah Thais, Daniel Murnane

Comments Paper at Knowledge and Logical Reasoning in the Era of Data-driven Learning Workshop at ICML 2023

Benign Overfitting for Two-layer ReLU Convolutional Neural Networks

Yiwen Kou, Zixiang Chen, Yuanzhou Chen, Quanquan Gu

Comments 45 pages, 3 figures, 2 tables. In ICML 2023

Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes

Jiafan He, Heyang Zhao, Dongruo Zhou, Quanquan Gu

Comments 33 pages, 1 table. In ICML 2023

Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms

Haoxiang Wang, Gargi Balasubramaniam, Haozhe Si, Bo Li, Han Zhao

Comments Submitted to JMLR. This journal version significantly extends our ICML 2022 paper, arXiv:2201.12919

Sequence Modeling with Multiresolution Convolutional Memory

Jiaxin Shi, Ke Alexander Wang, Emily B. Fox

Comments ICML 2023, Source code: https://github.com/thjashin/multires-conv

Gaussian Process Priors for Systems of Linear Partial Differential Equations with Constant Coefficients

Marc Härkönen, Markus Lange-Hegermann, Bogdan Raiţă

Comments 26 pages, 8 figures; ICML 2023 (oral); updated with expanded appendices and ancillary files. Code available at https://github.com/haerski/EPGP. For animations, see https://mathrepo.mis.mpg.de/EPGP/index.html. For a presentation see https://icml.cc/virtual/2023/oral/25571. The paper and all ancillary files are released under CC-BY

Journal ref ICML 2023 (oral); PMLR 202:12587-12615, 2023

Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection

Mohammad Azizmalayeri, Reza Abbasi, Amir Hosein Haji Mohammad rezaie, Reihaneh Zohrabi, Mahdi Amiri, Mohammad Taghi Manzuri, Mohammad Hossein Rohban

Comments Accepted at ICML 2023 Workshop on Spurious Correlations, Invariance, and Stability (SCIS)

The Acquisition of Physical Knowledge in Generative Neural Networks

Luca M. Schulze Buschoff, Eric Schulz, Marcel Binz

Comments Published as a conference paper at ICML 2023

On Many-Actions Policy Gradient

Michal Nauman, Marek Cygan

Comments ICML Proceedings 2023

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25769-25789, 2023

Inverse folding for antibody sequence design using deep learning

Frédéric A. Dreyer, Daniel Cutting, Constantin Schneider, Henry Kenlay, Charlotte M. Deane

Comments 2023 ICML Workshop on Computational Biology, model weights available at https://zenodo.org/record/8164693

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills

Seongun Kim, Kyowoon Lee, Jaesik Choi

Comments ICML 2023. First two authors contributed equally. Code at https://github.com/seongun-kim/vcrl

Data Augmentation for Emotion Detection in Small Imbalanced Text Data

Anna Koufakou, Diego Grisales, Ragy Costa de jesus, Oscar Fox

Comments To be published in the Proceedings of the 22nd IEEE International Conference on Machine Learning Applications (ICMLA 2023)

Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems

D'Jeff Kanda Nkashama, Arian Soltani, Jean-Charles Verdier, Marc Frappier, Pierre-Martin Tardif, Froduald Kabanza

Comments Machine Learning for Cybersecurity Workshop at the International Conference on Machine Learning(ICLR-ML4CY)

Inverse Decision Modeling: Learning Interpretable Representations of Behavior

Daniel Jarrett, Alihan Hüyük, Mihaela van der Schaar

Journal ref In Proc. 38th International Conference on Machine Learning (ICML 2021)

JAX FDM: A differentiable solver for inverse form-finding

Rafael Pastrana, Deniz Oktay, Ryan P. Adams, Sigrid Adriaenssens

Comments https://github.com/arpastrana/jax_fdm

Journal ref 40th International Conference on Machine Learning (2023: Differentiable Almost Everything Workshop

Dual Gauss-Newton Directions for Deep Learning

Vincent Roulet, Mathieu Blondel

Comments Presented at the Duality Principles for Modern Machine Learning Workshop at ICML 2023

Generalized Teacher Forcing for Learning Chaotic Dynamics

Florian Hess, Zahra Monfared, Manuel Brenner, Daniel Durstewitz

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

Journal ref PMLR 202:13017-13049, 2023

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, Beidi Chen

Journal ref Proceedings of the 40th International Conference on Machine Learning, 2023, 919