ICML

HAWQV3: Dyadic Neural Network Quantization

Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer

Journal ref ICML 2021

GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation Baselines

Sheng-Min Shih, Pin-Ju Tien, Zohar Karnin

Comments International Conference on Machine Learning 2021

PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data

Shreyas Malakarjun Patil, Constantine Dovrolis

Comments 19 pages, 13 figures, 1 table, International COnference on Machine Learning 2021

Emergent Social Learning via Multi-agent Reinforcement Learning

Kamal Ndousse, Douglas Eck, Sergey Levine, Natasha Jaques

Comments 14 pages, 19 figures. To be published in ICML 2021

SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

Alexander Wang, Mengye Ren, Richard S. Zemel

Comments ICML 2021

Dynamic Customer Embeddings for Financial Service Applications

Nima Chitsazan, Samuel Sharpe, Dwipam Katariya, Qianyu Cheng, Karthik Rajasethupathy

Comments ICML Workshop on Representation Learning for Finance and E-Commerce Applications

Towards Automated Evaluation of Explanations in Graph Neural Networks

Vanya BK, Balaji Ganesan, Aniket Saxena, Devbrat Sharma, Arvind Agarwal

Comments 5 pages, 4 figures, XAI Workshop at ICML 2021

Emphatic Algorithms for Deep Reinforcement Learning

Ray Jiang, Tom Zahavy, Zhongwen Xu, Adam White, Matteo Hessel, Charles Blundell, Hado van Hasselt

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Break-It-Fix-It: Unsupervised Learning for Program Repair

Michihiro Yasunaga, Percy Liang

Comments ICML 2021. Code & data available at https://github.com/michiyasunaga/bifi

DeepReDuce: ReLU Reduction for Fast Private Inference

Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen

Comments ICML 2021

Meta Adversarial Training against Universal Patches

Jan Hendrik Metzen, Nicole Finnie, Robin Hutmacher

Comments Accepted by the ICML 2021 workshop on "A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning"

Benchmarking Invertible Architectures on Inverse Problems

Jakob Kruse, Lynton Ardizzone, Carsten Rother, Ullrich Köthe

Journal ref Workshop on Invertible Neural Networks and Normalizing Flows (ICML 2019)

Data Augmentation for Meta-Learning

Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, Tom Goldstein

Comments 15 pages, 3 figures, Accepted to ICML 2021

Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes

Sebastian W. Ober, Laurence Aitchison

Comments Accepted for publication at the 38th International Conference on Machine Learning (ICML 2021, PMLR 139), 33 pages

Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification

Dong Hoon Lee, Sae-Young Chung

Comments Accepted to ICML 2021

A Turing Test for Transparency

Felix Biessmann, Viktor Treu

Comments Published in Proceedings of the ICML Workshop on Theoretical Foundations, Criticism, and Application Trends of Explainable AI held in conjunction with the 38th International Conference on Machine Learning (ICML)

f-Domain-Adversarial Learning: Theory and Algorithms

David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler

Comments ICML 2021

Policy Gradient Bayesian Robust Optimization for Imitation Learning

Zaynah Javed, Daniel S. Brown, Satvik Sharma, Jerry Zhu, Ashwin Balakrishna, Marek Petrik, Anca D. Dragan, Ken Goldberg

Comments In proceedings of the International Conference on Machine Learning (ICML) 2021

Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning

Matthieu Zimmer, Claire Glanois, Umer Siddique, Paul Weng

Comments International Conference on Machine Learning

How Do Adam and Training Strategies Help BNNs Optimization?

Zechun Liu, Zhiqiang Shen, Shichao Li, Koen Helwegen, Dong Huang, Kwang-Ting Cheng

Comments ICML 2021. Code and models are available at https://github.com/liuzechun/AdamBNN

Decadal Forecasts with ResDMD: a Residual DMD Neural Network

Eduardo Rodrigues, Bianca Zadrozny, Campbell Watson, David Gold

Comments Accepted to ICML 2021 Workshop Tackling Climate Change with Machine Learning

On Limited-Memory Subsampling Strategies for Bandits

Dorian Baudry, Yoan Russac, Olivier Cappé

Journal ref ICML 2021- International Conference on Machine Learning, Jul 2021, Vienna- Virtual, Austria

OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation

Jongmin Lee, Wonseok Jeon, Byung-Jun Lee, Joelle Pineau, Kee-Eung Kim

Comments 26 pages, 11 figures, Accepted at ICML 2021

Better Training using Weight-Constrained Stochastic Dynamics

Benedict Leimkuhler, Tiffany Vlaar, Timothée Pouchon, Amos Storkey

Comments ICML 2021 camera-ready. arXiv admin note: substantial text overlap with arXiv:2006.10114

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Deep Learning for Functional Data Analysis with Adaptive Basis Layers

Junwen Yao, Jonas Mueller, Jane-Ling Wang

Comments ICML 2021

Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes

Ji Won Park, Ashley Villar, Yin Li, Yan-Fei Jiang, Shirley Ho, Joshua Yao-Yu Lin, Philip J. Marshall, Aaron Roodman

Comments 6 pages, 4 figures, 1 table, written for non-astronomers, submitted to the ICML 2021 Time Series and Uncertainty and Robustness in Deep Learning Workshops. Comments welcome! Added affiliations and references for Fig 1

State Entropy Maximization with Random Encoders for Efficient Exploration

Younggyo Seo, Lili Chen, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

Comments ICML 2021. First two authors contributed equally. Website: https://sites.google.com/view/re3-rl Code: https://github.com/younggyoseo/RE3

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

Andrea Zanette

Comments Accepted to ICML 2021 as long talk

Outlier-Robust Optimal Transport

Debarghya Mukherjee, Aritra Guha, Justin Solomon, Yuekai Sun, Mikhail Yurochkin

Comments Accepted in Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Neural Rough Differential Equations for Long Time Series

James Morrill, Cristopher Salvi, Patrick Kidger, James Foster, Terry Lyons

Comments Published at ICML 2021