ICML

Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning

Rakshit Naidu, Harshita Diddee, Ajinkya Mulay, Aleti Vardhan, Krithika Ramesh, Ahmed Zamzam

Comments 4+3 pages; 6 figures; 8 tables. Accepted at SRML workshop at ICML'21

Kernel Continual Learning

Mohammad Mahdi Derakhshani, Xiantong Zhen, Ling Shao, Cees G. M. Snoek

Comments accepted to ICML 2021

HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections

Ines Chami, Albert Gu, Dat Nguyen, Christopher Ré

Comments ICML 2021

Journal ref PMLR 139:1419-1429, 2021

GMAC: A Distributional Perspective on Actor-Critic Framework

Daniel Wontae Nam, Younghoon Kim, Chan Y. Park

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7927-7936, 2021

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

Zehao Xiao, Jiayi Shen, Xiantong Zhen, Ling Shao, Cees G. M. Snoek

Comments accepted to ICML 2021

Disambiguation of weak supervision with exponential convergence rates

Vivien Cabannes, Francis Bach, Alessandro Rudi

Comments 22 pages; 6 figures

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

Conservative Objective Models for Effective Offline Model-Based Optimization

Brandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey Levine

Comments ICML 2021. First two authors contributed equally. Code at: https://github.com/brandontrabucco/design-baselines/blob/c65a53fe1e6567b740f0adf60c5db9921c1f2330/design_baselines/coms_cleaned/__init__.py

Core-set Sampling for Efficient Neural Architecture Search

Jae-hun Shim, Kyeongbo Kong, Suk-Ju Kang

Comments 8 pages, 2 figures, spotlight presented at the ICML 2021 Workshop on Subset Selection in ML

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks

Yukun Yang, Wenrui Zhang, Peng Li

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

Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot

Joel Z. Leibo, Edgar Duéñez-Guzmán, Alexander Sasha Vezhnevets, John P. Agapiou, Peter Sunehag, Raphael Koster, Jayd Matyas, Charles Beattie, Igor Mordatch, Thore Graepel

Comments Accepted to ICML 2021 and presented as a long talk; 33 pages; 9 figures

Journal ref In International Conference on Machine Learning 2021 (pp. 6187-6199). PMLR

Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs

Shruthi Bannur, Ozan Oktay, Melanie Bernhardt, Anton Schwaighofer, Rajesh Jena, Besmira Nushi, Sharan Wadhwani, Aditya Nori, Kal Natarajan, Shazad Ashraf, Javier Alvarez-Valle, Daniel C. Castro

Comments Presented at ICML 2021 Workshop on Interpretable Machine Learning in Healthcare

Oblivious sketching for logistic regression

Alexander Munteanu, Simon Omlor, David Woodruff

Comments ICML 2021

Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning

Jack Lynch, Sam Wookey

Comments Tackling Climate Change with Machine Learning Workshop at ICML 2021

Approximating a Target Distribution using Weight Queries

Nadav Barak, Sivan Sabato

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:674-683, 2021

AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense

Duhun Hwang, Eunjung Lee, Wonjong Rhee

Journal ref ICML 2021 Workshop on Adversarial Machine Learning

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Mehdi Fatemi, Honglak Lee

Comments In proceedings of ICML 2021

Interaction-Grounded Learning

Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad

Comments Published in ICML 2021

Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen

Comments Published at ICML 2021, Code @ https://github.com/Felix-Petersen/diffsort, Video @ https://www.youtube.com/watch?v=38dvqdYEs1o

Journal ref PMLR 139:8546-8555, 2021

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels

Zhaowei Zhu, Yiwen Song, Yang Liu

Comments ICML 2021

Information-Guided Sampling for Low-Rank Matrix Completion

Simon Mak, Henry Shaowu Yushi, Yao Xie

Comments ICML 2021 Workshop on Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning

Fast-Slow Streamflow Model Using Mass-Conserving LSTM

Miguel Paredes Quiñones, Maciel Zortea, Leonardo S. A. Martins

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

Automated Learning Rate Scheduler for Large-batch Training

Chiheon Kim, Saehoon Kim, Jongmin Kim, Donghoon Lee, Sungwoong Kim

Comments 15 pages, 7 figures, 4 tables, 8th ICML Workshop on Automated Machine Learning (2021)

Few-shot Language Coordination by Modeling Theory of Mind

Hao Zhu, Graham Neubig, Yonatan Bisk

Comments Thirty-eighth International Conference on Machine Learning (ICML 2021)

Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff

Mitchell Naylor, Christi French, Samantha Terker, Uday Kamath

Comments To appear at Interpretable ML in Healthcare workshop at ICML 2021. 9 pages (excluding references), 6 figures

L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation

Christian S. Perone, Roberto Pereira Silveira, Thomas Paula

Comments 6 pages, 1 figure, accepted for ICML 2021 UDL Workshop

Hölder Bounds for Sensitivity Analysis in Causal Reasoning

Serge Assaad, Shuxi Zeng, Henry Pfister, Fan Li, Lawrence Carin

Comments Workshop on the Neglected Assumptions in Causal Inference at the International Conference on Machine Learning (ICML), 2021

Equivariant Graph Neural Networks for 3D Macromolecular Structure

Bowen Jing, Stephan Eismann, Pratham N. Soni, Ron O. Dror

Comments WCB @ ICML 2021 + link to code

Stability and Generalization of Stochastic Gradient Methods for Minimax Problems

Yunwen Lei, Zhenhuan Yang, Tianbao Yang, Yiming Ying

Comments To appear in ICML 2021 as Long Presentation

A resource-efficient method for repeated HPO and NAS problems

Giovanni Zappella, David Salinas, Cédric Archambeau

Comments Accepted at AutoML workshop @ ICML 2021

On Proximal Policy Optimization's Heavy-tailed Gradients

Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Zachary C. Lipton, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Pradeep Ravikumar

Comments ICML 2021