ICML

Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning

Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli

Journal ref Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

Disentangling Trainability and Generalization in Deep Neural Networks

Lechao Xiao, Jeffrey Pennington, Samuel S. Schoenholz

Comments 22 pages, 3 figures, ICML 2020. Associated Colab notebook at https://colab.research.google.com/github/google/neural-tangents/blob/master/notebooks/Disentangling_Trainability_and_Generalization.ipynb

Multi-step Greedy Reinforcement Learning Algorithms

Manan Tomar, Yonathan Efroni, Mohammad Ghavamzadeh

Comments ICML 2020

Is Machine Learning Speaking my Language? A Critical Look at the NLP-Pipeline Across 8 Human Languages

Esma Wali, Yan Chen, Christopher Mahoney, Thomas Middleton, Marzieh Babaeianjelodar, Mariama Njie, Jeanna Neefe Matthews

Comments Participatory Approaches to Machine Learning Workshop, 37th International Conference on Machine Learning

Representation Learning via Adversarially-Contrastive Optimal Transport

Anoop Cherian, Shuchin Aeron

Comments Accepted at ICML 2020

Graph Neural Networks for Massive MIMO Detection

Andrea Scotti, Nima N. Moghadam, Dong Liu, Karl Gafvert, Jinliang Huang

Comments ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+)

Vizarel: A System to Help Better Understand RL Agents

Shuby Deshpande, Jeff Schneider

Comments Accepted to ICML 2020 Workshop on Human Interpretability in Machine Learning (Spotlight)

Solving Constrained CASH Problems with ADMM

Parikshit Ram, Sijia Liu, Deepak Vijaykeerthi, Dakuo Wang, Djallel Bouneffouf, Greg Bramble, Horst Samulowitz, Alexander G. Gray

Comments 7th ICML Workshop on Automated Machine Learning (2020)

Robust model training and generalisation with Studentising flows

Simon Alexanderson, Gustav Eje Henter

Comments 9 pages, 8 figures, accepted for publication at INNF+ 2020 (Second ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models)

Population-Based Black-Box Optimization for Biological Sequence Design

Christof Angermueller, David Belanger, Andreea Gane, Zelda Mariet, David Dohan, Kevin Murphy, Lucy Colwell, D Sculley

Journal ref Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

The Tree Ensemble Layer: Differentiability meets Conditional Computation

Hussein Hazimeh, Natalia Ponomareva, Petros Mol, Zhenyu Tan, Rahul Mazumder

Comments ICML 2020

Adversarial Filters of Dataset Biases

Ronan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers, Matthew E. Peters, Ashish Sabharwal, Yejin Choi

Comments Accepted to ICML 2020

Robust Learning with the Hilbert-Schmidt Independence Criterion

Daniel Greenfeld, Uri Shalit

Comments Proceedings of the 37th International Conference on Machine Learning (ICML 2020)

Not Your Grandfathers Test Set: Reducing Labeling Effort for Testing

Begum Taskazan, Jiri Navratil, Matthew Arnold, Anupama Murthi, Ganesh Venkataraman, Benjamin Elder

Comments International Workshop on Challenges in Deploying and Monitoring Machine Learning Systems in Conjunction with ICML 2020

Impact of Legal Requirements on Explainability in Machine Learning

Adrien Bibal, Michael Lognoul, Alexandre de Streel, Benoît Frénay

Comments ICML Workshop on Law and Machine Learning

Characteristics of Monte Carlo Dropout in Wide Neural Networks

Joachim Sicking, Maram Akila, Tim Wirtz, Sebastian Houben, Asja Fischer

Comments Accepted at the ICML 2020 workshop for Uncertainty and Robustness in Deep Learning

Learning Heat Diffusion for Network Alignment

Sisi Qu, Mengmeng Xu, Bernard Ghanem, Jesper Tegner

Comments 4 Pages, 2 figures

Journal ref Presented at the ICML 2020 Workshop on Computational Biology (WCB)

Robust Classification under Class-Dependent Domain Shift

Tigran Galstyan, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

Comments Accepted at ICML 2020 workshop on Uncertainty and Robustness in Deep Learning

Integrating Logical Rules Into Neural Multi-Hop Reasoning for Drug Repurposing

Yushan Liu, Marcel Hildebrandt, Mitchell Joblin, Martin Ringsquandl, Volker Tresp

Comments Accepted at the ICML 2020 Workshop Graph Representation Learning and Beyond (GRL+)

Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning

Matthias Hutsebaut-Buysse, Kevin Mets, Steven Latré

Comments Paper accepted to the ICML 2020 Language in Reinforcement Learning (LaReL) Workshop

AdaScale SGD: A User-Friendly Algorithm for Distributed Training

Tyler B. Johnson, Pulkit Agrawal, Haijie Gu, Carlos Guestrin

Comments ICML 2020

Adaptive Braking for Mitigating Gradient Delay

Abhinav Venigalla, Atli Kosson, Vitaliy Chiley, Urs Köster

Comments In Beyond First Order Methods in ML Systems workshop at the 37th International Conference on Machine Learning, 2020

An Imitation Learning Approach for Cache Replacement

Evan Zheran Liu, Milad Hashemi, Kevin Swersky, Parthasarathy Ranganathan, Junwhan Ahn

Comments International Conference on Machine Learning (ICML), 2020

On the Iteration Complexity of Hypergradient Computation

Riccardo Grazzi, Luca Franceschi, Massimiliano Pontil, Saverio Salzo

Comments accepted at ICML 2020; 19 pages, 4 figures; code at https://github.com/prolearner/hypertorch (corrected typos and one reference)

Options as responses: Grounding behavioural hierarchies in multi-agent RL

Alexander Sasha Vezhnevets, Yuhuai Wu, Remi Leblond, Joel Z. Leibo

Comments First two authors contributed equally

Journal ref International Conference on Machine Learning 2020

One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control

Wenlong Huang, Igor Mordatch, Deepak Pathak

Comments Accepted at ICML 2020. Videos and code at https://huangwl18.github.io/modular-rl/

Multinomial Logit Bandit with Low Switching Cost

Kefan Dong, Yingkai Li, Qin Zhang, Yuan Zhou

Comments Accepted for presentation at the International Conference on Machine Learning (ICML) 2020

Predicting Court Decisions for Alimony: Avoiding Extra-legal Factors in Decision made by Judges and Not Understandable AI Models

Fabrice Muhlenbach, Long Nguyen Phuoc, Isabelle Sayn

Comments Extended version of the poster accepted at the first ICML Workshop on "Law and Machine Learning". https://sites.google.com/view/icml-law-and-ml-2020/

Client Adaptation improves Federated Learning with Simulated Non-IID Clients

Laura Rieger, Rasmus M. Th. Høegh, Lars K. Hansen

Comments 11 pages, 11 figures. To appear at International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020

Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint

Vihari Piratla, Shiv Shankar

Comments 6 pages, ICML 2020 Workshop on Uncertainty and Ro-bustness in Deep Learning