ICML

Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence

Yun Kuen Cheung, Georgios Piliouras

Comments In ICML 2021

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

Alexander Immer, Matthias Bauer, Vincent Fortuin, Gunnar Rätsch, Mohammad Emtiyaz Khan

Comments ICML 2021

Learning in Nonzero-Sum Stochastic Games with Potentials

David Mguni, Yutong Wu, Yali Du, Yaodong Yang, Ziyi Wang, Minne Li, Ying Wen, Joel Jennings, Jun Wang

Comments ICML 2021

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

Haitian Sun, Pat Verga, Bhuwan Dhingra, Ruslan Salakhutdinov, William W. Cohen

Comments Accepted at the 38th International Conference on Machine Learning, PMLR 139, 2021

Interactive Learning from Activity Description

Khanh Nguyen, Dipendra Misra, Robert Schapire, Miro Dudík, Patrick Shafto

Comments ICML 2021

Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training

Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy

Comments 16 pages; 10 figures; Published in Proceedings of the 38th International Conference on Machine Learning. Code can be found https://github.com/Shiweiliuiiiiiii/In-Time-Over-Parameterization

Journal ref Proceedings of the 38th International Conference on Machine Learning (2021)

Selfish Sparse RNN Training

Shiwei Liu, Decebal Constantin Mocanu, Yulong Pei, Mykola Pechenizkiy

Comments Published in Proceedings of the 38th International Conference on Machine Learning. Code can be found in https://github.com/Shiweiliuiiiiiii/Selfish-RNN

Journal ref Proceedings of the 38th International Conference on Machine Learning (2021)

Graph cuts always find a global optimum for Potts models (with a catch)

Hunter Lang, David Sontag, Aravindan Vijayaraghavan

Comments Published at ICML 2021. 18 pages, 2 figures

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

Wenxiao Wang, Minghao Chen, Shuai Zhao, Long Chen, Jinming Hu, Haifeng Liu, Deng Cai, Xiaofei He, Wei Liu

Comments 11 pages, 5 figures. Accepted by ICML 2021

Characterizing Structural Regularities of Labeled Data in Overparameterized Models

Ziheng Jiang, Chiyuan Zhang, Kunal Talwar, Michael C. Mozer

Comments 17 pages, 20 figures, ICML 2021

Unsupervised Learning of Visual 3D Keypoints for Control

Boyuan Chen, Pieter Abbeel, Deepak Pathak

Comments Accepted at ICML 2021. Videos and code at https://buoyancy99.github.io/unsup-3d-keypoints/

PopSkipJump: Decision-Based Attack for Probabilistic Classifiers

Carl-Johann Simon-Gabriel, Noman Ahmed Sheikh, Andreas Krause

Comments ICML'21. Code available at https://github.com/cjsg/PopSkipJump . 9 pages & 7 figures in main part, 14 pages & 10 figures in appendix

On-Policy Deep Reinforcement Learning for the Average-Reward Criterion

Yiming Zhang, Keith W. Ross

Comments International Conference on Machine Learning (ICML) 2021

Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation

Xiang Lin, Simeng Han, Shafiq Joty

Comments ICML 2021

Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization

Shahana Ibrahim, Xiao Fu

Comments To appear in ICML 2021

Temporal Predictive Coding For Model-Based Planning In Latent Space

Tung Nguyen, Rui Shu, Tuan Pham, Hung Bui, Stefano Ermon

Comments International Conference on Machine Learning

SinIR: Efficient General Image Manipulation with Single Image Reconstruction

Jihyeong Yoo, Qifeng Chen

Comments Accepted to ICML 2021

On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

Zahra Babaiee, Ramin Hasani, Mathias Lechner, Daniela Rus, Radu Grosu

Comments 21 Pages. Accepted for publication in the proceedings of the 38th International Conference on Machine Learning (ICML) 2021

Characterizing the Gap Between Actor-Critic and Policy Gradient

Junfeng Wen, Saurabh Kumar, Ramki Gummadi, Dale Schuurmans

Comments ICML 2021

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

Shai Keynan, Elad Sarafian, Sarit Kraus

Comments ICML 2021

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

Xiaohui Chen, Xu Han, Jiajing Hu, Francisco J. R. Ruiz, Liping Liu

Comments ICML 2021

Breaking the Limits of Message Passing Graph Neural Networks

Muhammet Balcilar, Pierre Héroux, Benoit Gaüzère, Pascal Vasseur, Sébastien Adam, Paul Honeine

Comments 18 pages, 6 figures

Journal ref The Thirty-eighth International Conference on Machine Learning, ICML2021

On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework

Zeyu Yan, Fei Wen, Rendong Ying, Chao Ma, Peilin Liu

Comments ICML 2021

Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps

Renyi Chen, Molei Tao

Comments 17 pages, 7 figures. ICML 2021

Active Testing: Sample-Efficient Model Evaluation

Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth

Comments Published at the 38th International Conference on Machine Learning (ICML 2021)

Three Operator Splitting with a Nonconvex Loss Function

Alp Yurtsever, Varun Mangalick, Suvrit Sra

Comments Appears in Proceedings of the 38th International Conference on Machine Learning (ICML 2021)

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, Stéphane Deny

Comments 13 pages, 6 figures, to appear at ICML 2021

Continuous Coordination As a Realistic Scenario for Lifelong Learning

Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron Courville, Sarath Chandar

Comments 19 pages with supplementary materials. Added results for Lifelong RL methods and some future work. Accepted to ICML 2021

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

Cristian Bodnar, Fabrizio Frasca, Yu Guang Wang, Nina Otter, Guido Montúfar, Pietro Liò, Michael Bronstein

Comments ICML 2021. Contains 27 pages, 9 figures

Understanding and Mitigating Accuracy Disparity in Regression

Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon, Han Zhao

Comments ICML 2021