ICML

Nyström Kernel Mean Embeddings

Antoine Chatalic, Nicolas Schreuder, Alessandro Rudi, Lorenzo Rosasco

Comments 8 pages

Journal ref ICML 2022

PDE-Based Optimal Strategy for Unconstrained Online Learning

Zhiyu Zhang, Ashok Cutkosky, Ioannis Paschalidis

Comments ICML 2022

Ripple Attention for Visual Perception with Sub-quadratic Complexity

Lin Zheng, Huijie Pan, Lingpeng Kong

Comments 19 pages, 2 figures, ICML 2022 camera ready

EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning

Shay Vargaftik, Ran Ben Basat, Amit Portnoy, Gal Mendelson, Yaniv Ben-Itzhak, Michael Mitzenmacher

Comments To appear in ICML 2022

Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models

Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu, Bo Zhang

Comments Accepted in ICML 2022

Differentiable Top-k Classification Learning

Felix Petersen, Hilde Kuehne, Christian Borgelt, Oliver Deussen

Comments Published at ICML 2022, Code @ https://github.com/Felix-Petersen/difftopk

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator

Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky, Peter J. Ramadge

Comments Accepted at the International Conference on Machine Learning (ICML) 2022. The first two authors contributed equally

Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning

Shentao Yang, Yihao Feng, Shujian Zhang, Mingyuan Zhou

Comments International Conference on Machine Learning (ICML) 2022

Combining Counterfactuals With Shapley Values To Explain Image Models

Aditya Lahiri, Kamran Alipour, Ehsan Adeli, Babak Salimi

Journal ref ICML 2022 Workshop on Responsible Decision Making in Dynamic Environments

On the Role of Discount Factor in Offline Reinforcement Learning

Hao Hu, Yiqin Yang, Qianchuan Zhao, Chongjie Zhang

Comments Thirty-ninth International Conference on Machine Learning

HyperPrompt: Prompt-based Task-Conditioning of Transformers

Yun He, Huaixiu Steven Zheng, Yi Tay, Jai Gupta, Yu Du, Vamsi Aribandi, Zhe Zhao, YaGuang Li, Zhao Chen, Donald Metzler, Heng-Tze Cheng, Ed H. Chi

Comments Accepted to ICML 2022

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Jaehyeong Jo, Seul Lee, Sung Ju Hwang

Comments ICML 2022

You Only Cut Once: Boosting Data Augmentation with a Single Cut

Junlin Han, Pengfei Fang, Weihao Li, Jie Hong, Mohammad Ali Armin, Ian Reid, Lars Petersson, Hongdong Li

Comments ICML 2022, Code: https://github.com/JunlinHan/YOCO

MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection

Zhenhong Sun, Ming Lin, Xiuyu Sun, Zhiyu Tan, Hao Li, Rong Jin

Comments Accepted by ICML 2022

RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests

Victor Chernozhukov, Whitney K. Newey, Victor Quintas-Martinez, Vasilis Syrgkanis

Comments Accepted for a long presentation at the ICML. Code available at https://github.com/victor5as/RieszLearning

Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations

Abubakar Abid, Mert Yuksekgonul, James Zou

Comments ICML 2022

Re-evaluating Word Mover's Distance

Ryoma Sato, Makoto Yamada, Hisashi Kashima

Comments ICML 2022

Adversarial Vulnerability of Randomized Ensembles

Hassan Dbouk, Naresh R. Shanbhag

Comments Published as a conference paper in ICML 2022

Confidence Score for Source-Free Unsupervised Domain Adaptation

Jonghyun Lee, Dahuin Jung, Junho Yim, Sungroh Yoon

Comments ICML 2022 camera ready

Transformers are Meta-Reinforcement Learners

Luckeciano C. Melo

Comments Published at the International Conference on Machine Learning (ICML) 2022

Permutation Search of Tensor Network Structures via Local Sampling

Chao Li, Junhua Zeng, Zerui Tao, Qibin Zhao

Comments Accepted by ICML 2022

On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis

Qi Lyu, Xiao Fu

Comments Accepted to ICML 2022, 19 pages, 4 figures

Memory-Based Model Editing at Scale

Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning, Chelsea Finn

Comments ICML 2022. Project site at https://sites.google.com/view/serac-editing

Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training

Charbel Sakr, Steve Dai, Rangharajan Venkatesan, Brian Zimmer, William J. Dally, Brucek Khailany

Comments Published as a spotlight paper at ICML 2022. Paper contains 16 pages, 5 figures, and 6 tables

A Functional Information Perspective on Model Interpretation

Itai Gat, Nitay Calderon, Roi Reichart, Tamir Hazan

Comments Accepted to ICML 2022

Neural Laplace: Learning diverse classes of differential equations in the Laplace domain

Samuel Holt, Zhaozhi Qian, Mihaela van der Schaar

Comments Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022. Copyright 2022 by the author(s)

On the Convergence of the Shapley Value in Parametric Bayesian Learning Games

Lucas Agussurja, Xinyi Xu, Bryan Kian Hsiang Low

Comments Accepted to the 39th International Conference on Machine Learning (ICML 2022). Extended version with derivations

General-purpose, long-context autoregressive modeling with Perceiver AR

Curtis Hawthorne, Andrew Jaegle, Cătălina Cangea, Sebastian Borgeaud, Charlie Nash, Mateusz Malinowski, Sander Dieleman, Oriol Vinyals, Matthew Botvinick, Ian Simon, Hannah Sheahan, Neil Zeghidour, Jean-Baptiste Alayrac, João Carreira, Jesse Engel

Comments ICML 2022

Benchmarking and Analyzing Point Cloud Classification under Corruptions

Jiawei Ren, Liang Pan, Ziwei Liu

Comments ICML 2022; Code and dataset are available at https://github.com/jiawei-ren/modelnetc

A Consistent and Efficient Evaluation Strategy for Attribution Methods

Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci

Comments 26 pages. Accepted at ICML 2022