ICML

ARRID: ANN-based Rotordynamics for Robust and Integrated Design

Soheyl Massoudi, Jürg Schiffmann

Comments Submitted to Machine Learning in Computational Design Workshop of the 39th International Conference on Machine Learning, 2022, 4 pages, 1 figure

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces

Yinshuang Xu, Jiahui Lei, Edgar Dobriban, Kostas Daniilidis

Comments Accepted at ICML2022 Thirty-ninth International Conference on Machine Learning

Causal Strategic Linear Regression

Yonadav Shavit, Benjamin Edelman, Brian Axelrod

Comments 18 pages; published at ICML 2020

SPDY: Accurate Pruning with Speedup Guarantees

Elias Frantar, Dan Alistarh

Comments ICML 2022

Do Differentiable Simulators Give Better Policy Gradients?

H. J. Terry Suh, Max Simchowitz, Kaiqing Zhang, Russ Tedrake

Comments Accepted to ICML 2022

Journal ref ICML 2022

Improving Task-free Continual Learning by Distributionally Robust Memory Evolution

Zhenyi Wang, Li Shen, Le Fang, Qiuling Suo, Tiehang Duan, Mingchen Gao

Comments ICML 2022

Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback

Fang Kong, Yichi Zhou, Shuai Li

Comments Published in ICML 2022

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks

Quynh Nguyen, Marco Mondelli, Guido Montufar

Comments appeared at ICML 2021, this version corrects a mistake in Lemma 5.4 which also affects Lemma 5.5. These two Lemmas have been edited and the corresponding proofs corrected. All the other results remain untouched

Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control

Weichao Mao, Kaiqing Zhang, Ruihao Zhu, David Simchi-Levi, Tamer Başar

Comments A preliminary version of this work has appeared in ICML 2021

Graph Convolutional Networks from the Perspective of Sheaves and the Neural Tangent Kernel

Thomas Gebhart

Comments Part of ICML 2022 Workshop on Topology, Algebra, and Geometry in Machine Learning

GraphTTA: Test Time Adaptation on Graph Neural Networks

Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li

Comments ICML 2022 Workshop "Principles of Distribution Shift"

Certified Adversarial Robustness via Anisotropic Randomized Smoothing

Hanbin Hong, Yuan Hong

Comments Submitted to ICML 2022

On the Surprising Behaviour of node2vec

Celia Hacker, Bastian Rieck

Comments ICML 2022 Workshop on Topology, Algebra, and Geometry in Machine Learning (Camera-Ready Version)

How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation

Yujin Kim, Jaehoon Oh, Sungnyun Kim, Se-Young Yun

Comments 18 pages, 25 figures, 11 tables; previous version was presented at ICML UpML workshop, 2022

Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis

Stefan Röhrl, Alice Hein, Lucie Huang, Dominik Heim, Christian Klenk, Manuel Lengl, Martin Knopp, Nawal Hafez, Oliver Hayden, Klaus Diepold

Comments Presented at the 2nd Workshop on Interpretable Machine Learning in Healthcare (IMLH) @ ICML 2022

Generative Thermal Design Through Boundary Representation and Multi-Agent Cooperative Environment

Hadi Keramati, Feridun Hamdullahpur

Journal ref ICML 2022 Workshop on Machine Learning in Computational Design

GreenDB -- A Dataset and Benchmark for Extraction of Sustainability Information of Consumer Goods

Sebastian Jäger, Alexander Flick, Jessica Adriana Sanchez Garcia, Kaspar von den Driesch, Karl Brendel, Felix Biessmann

Comments Presented at DataPerf Workshop at the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, 2022

An initial alignment between neural network and target is needed for gradient descent to learn

Emmanuel Abbe, Elisabetta Cornacchia, Jan Hązła, Christopher Marquis

Journal ref Proceedings of the International Conference on Machine Learning, 2022

Federated Learning with Partial Model Personalization

Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi, Lin Xiao

Journal ref ICML 2022: 17716-17758

Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere

Tongzhou Wang, Phillip Isola

Comments International Conference on Machine Learning (ICML), 2020

Federated Learning with Positive and Unlabeled Data

Xinyang Lin, Hanting Chen, Yixing Xu, Chao Xu, Xiaolin Gui, Yiping Deng, Yunhe Wang

Journal ref ICML 2022

$C^*$-algebra Net: A New Approach Generalizing Neural Network Parameters to $C^*$-algebra

Yuka Hashimoto, Zhao Wang, Tomoko Matsui

Comments Accepted at ICML 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:8523-8534, 2022

Estimating and Penalizing Induced Preference Shifts in Recommender Systems

Micah Carroll, Anca Dragan, Stuart Russell, Dylan Hadfield-Menell

Comments Accepted to ICML 2022 (Spotlight)

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:2686-2708, 2022

Latent Variable Models for Bayesian Causal Discovery

Jithendaraa Subramanian, Yashas Annadani, Ivaxi Sheth, Stefan Bauer, Derek Nowrouzezahrai, Samira Ebrahimi Kahou

Comments 7 figures, Published at the ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability

Steerable 3D Spherical Neurons

Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck

Comments ICML2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:15330-15339, 2022. https://proceedings.mlr.press/v162/melnyk22a.html

Ad Hoc Teamwork in the Presence of Adversaries

Ted Fujimoto, Samrat Chatterjee, Auroop Ganguly

Comments Blue Sky Ideas Acceptance at the New Frontiers in Adversarial Machine Learning Workshop @ ICML 2022

On the Importance of Critical Period in Multi-stage Reinforcement Learning

Junseok Park, Inwoo Hwang, Min Whoo Lee, Hyunseok Oh, Minsu Lee, Youngki Lee, Byoung-Tak Zhang

Comments Accepted by the ICML Complex Feedback in Online Learning Workshop (Open Problems) 2022

Gradient Flows for L2 Support Vector Machine Training

Christian Bauckhage, Helen Schneider, Benjamin Wulff, Rafet Sifa

Comments Peer-reviewed and presented as part of the workshop on Continuous Time Methods for Machine Learning at the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, 2022

The Unsurprising Effectiveness of Pre-Trained Vision Models for Control

Simone Parisi, Aravind Rajeswaran, Senthil Purushwalkam, Abhinav Gupta

Comments First two authors contributed equally

Journal ref International Conference on Machine Learning (ICML), 2022, 162:17359-17371

Neural Message Passing for Visual Relationship Detection

Yue Hu, Siheng Chen, Xu Chen, Ya Zhang, Xiao Gu

Comments Accepted by ICML LRG Workshop 2019