ICML

Interpreting diffusion score matching using normalizing flow

Wenbo Gong, Yingzhen Li

Comments 8 pages, International Conference on Machine Learning (ICML) INNF+ 2021 Workshop Spotlight

Adaptive Inducing Points Selection For Gaussian Processes

Théo Galy-Fajou, Manfred Opper

Comments Accepted at Continual Learning Workshop - ICML 2020 : https://sites.google.com/view/cl-icml/home

Online structural kernel selection for mobile health

Eura Shin, Pedja Klasnja, Susan Murphy, Finale Doshi-Velez

Comments Workshop paper in ICML IMLH 2021

Defending against Reconstruction Attack in Vertical Federated Learning

Jiankai Sun, Yuanshun Yao, Weihao Gao, Junyuan Xie, Chong Wang

Comments Accepted to International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021 (FL-ICML'21)

Statistical Estimation from Dependent Data

Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, Surbhi Goel, Anthimos Vardis Kandiros

Comments 41 pages, ICML 2021

Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions

Eoin Delaney, Derek Greene, Mark T. Keane

Journal ref ICML Workshop on Algorithmic Recourse, July 2021

Structured Model Pruning of Convolutional Networks on Tensor Processing Units

Kongtao Chen, Ken Franko, Ruoxin Sang

Comments International Conference on Machine Learning 2021 Workshop on Overparameterization: Pitfalls & Opportunities

Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment

Michael Chang, Sidhant Kaushik, Sergey Levine, Thomas L. Griffiths

Comments Long Presentation at the Thirty-eighth International Conference on Machine Learning (ICML) 2021. 21 pages, 11 figures. v2: updated acknowledgments. v3: clarified that the internal function nodes of the credit assignment mechanism are not considered O(1)

Self-Tuning for Data-Efficient Deep Learning

Ximei Wang, Jinghan Gao, Mingsheng Long, Jianmin Wang

Comments 11 pages, 7 figures

Journal ref ICML 2021, https://icml.cc/virtual/2021/spotlight/8616

Active Slices for Sliced Stein Discrepancy

Wenbo Gong, Kaibo Zhang, Yingzhen Li, José Miguel Hernández-Lobato

Comments 22 pages, 7 figures, International Conference on Machine Learning (ICML) 2021

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth

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

Offline Meta-Reinforcement Learning with Advantage Weighting

Eric Mitchell, Rafael Rafailov, Xue Bin Peng, Sergey Levine, Chelsea Finn

Comments ICML 2021; for code & project info, see http://sites.google.com/view/macaw-metarl

Learn2Hop: Learned Optimization on Rough Landscapes

Amil Merchant, Luke Metz, Sam Schoenholz, Ekin Dogus Cubuk

Comments ICML 2021, 16 pages, 8 figures, 6 tables

Generative Video Transformer: Can Objects be the Words?

Yi-Fu Wu, Jaesik Yoon, Sungjin Ahn

Comments Published in ICML 2021

Examining the Human Perceptibility of Black-Box Adversarial Attacks on Face Recognition

Benjamin Spetter-Goldstein, Nataniel Ruiz, Sarah Adel Bargal

Comments 5 pages, 5 figures, submitted to AdvML @ ICML 2021

A comparative study of stochastic and deep generative models for multisite precipitation synthesis

Jorge Guevara, Dario Borges, Campbell Watson, Bianca Zadrozny

Comments ICML 2021 Workshop Tackling Climate Change with Machine Learning

Quantification of Carbon Sequestration in Urban Forests

Levente J. Klein, Wang Zhou, Conrad M. Albrecht

Journal ref International Conference on Machine Learning (ICML 2021) Workshop

Distribution-free calibration guarantees for histogram binning without sample splitting

Chirag Gupta, Aaditya K. Ramdas

Comments Appears at ICML 2021 (http://proceedings.mlr.press/v139/gupta21b.html)

Reinforcement Learning with Prototypical Representations

Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto

Journal ref ICML 2021

A Theory of Label Propagation for Subpopulation Shift

Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei

Comments ICML 2021

Few-shot Conformal Prediction with Auxiliary Tasks

Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

Comments ICML camera ready

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification

Yu Bai, Song Mei, Huan Wang, Caiming Xiong

Comments Appearing at ICML 2021

Towards Domain-Agnostic Contrastive Learning

Vikas Verma, Minh-Thang Luong, Kenji Kawaguchi, Hieu Pham, Quoc V. Le

Comments Published in ICML 2021

Reinforcement Learning Under Moral Uncertainty

Adrien Ecoffet, Joel Lehman

Comments 28 pages, 18 figures; update adds discussion of a possible flaw of Nash voting, discussion of further possible research into MEC, as well as a few more references; updated to ICML version

Over-Parameterization and Generalization in Audio Classification

Khaled Koutini, Hamid Eghbal-zadeh, Florian Henkel, Jan Schlüter, Gerhard Widmer

Comments Presented at the ICML 2021 Workshop on Overparameterization: Pitfalls & Opportunities

On Out-of-distribution Detection with Energy-based Models

Sven Elflein, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann

Comments Accepted to ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning

Structured World Belief for Reinforcement Learning in POMDP

Gautam Singh, Skand Peri, Junghyun Kim, Hyunseok Kim, Sungjin Ahn

Comments Published in ICML 2021

Unsupervised Skill-Discovery and Skill-Learning in Minecraft

Juan José Nieto, Roger Creus, Xavier Giro-i-Nieto

Comments Accepted at ICML Unsupervised RL Workshop, 8 pages

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

Kevin Li, Abhishek Gupta, Ashwin Reddy, Vitchyr Pong, Aurick Zhou, Justin Yu, Sergey Levine

Comments Accepted to ICML 2021. First two authors contributed equally

Safe Reinforcement Learning Using Advantage-Based Intervention

Nolan Wagener, Byron Boots, Ching-An Cheng

Comments Appearing in ICML 2021. 29 pages, 8 figures