ICML

SparseBERT: Rethinking the Importance Analysis in Self-attention

Han Shi, Jiahui Gao, Xiaozhe Ren, Hang Xu, Xiaodan Liang, Zhenguo Li, James T. Kwok

Comments Accepted by ICML 2021

Robust Asymmetric Learning in POMDPs

Andrew Warrington, J. Wilder Lavington, Adam Ścibior, Mark Schmidt, Frank Wood

Comments ICML 2021

World Model as a Graph: Learning Latent Landmarks for Planning

Lunjun Zhang, Ge Yang, Bradly C. Stadie

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

COVID-19 Screening Using Residual Attention Network an Artificial Intelligence Approach

Vishal Sharma, Curtis Dyreson

Journal ref 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)

The Power of Adaptivity for Stochastic Submodular Cover

Rohan Ghuge, Anupam Gupta, Viswanath Nagarajan

Comments In proceedings of ICML 2021

Differentiable Particle Filtering via Entropy-Regularized Optimal Transport

Adrien Corenflos, James Thornton, George Deligiannidis, Arnaud Doucet

Comments 9 pages of content + 11 pages supplementary, accepted for oral at ICML 2021

Scalable Normalizing Flows for Permutation Invariant Densities

Marin Biloš, Stephan Günnemann

Comments International Conference on Machine Learning (ICML) 2021

Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks

Ting-Wu Chin, Ari S. Morcos, Diana Marculescu

Comments Accepted at ECML-PKDD 2021 (Research Track), 4-page abridged versions have been accepted at non-archival venues including RealML and DMMLSys workshops at ICML'20 and DLP-KDD and AdvML workshops at KDD'20

Safe Option-Critic: Learning Safety in the Option-Critic Architecture

Arushi Jain, Khimya Khetarpal, Doina Precup

Comments To appear at The Knowledge Engineering Review (KER), 2021. Previous draft appeared in Adaptive Learning Agents (ALA) 2018 workshop held at ICML, AAMAS in Stockholm. Corrected typos, added references and added extra figures

Journal ref The Knowledge Engineering Review 36 (2021) e4

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning

Nikunj Saunshi, Arushi Gupta, Wei Hu

Comments In proceedings of ICML 2021

Attentive Neural Processes and Batch Bayesian Optimization for Scalable Calibration of Physics-Informed Digital Twins

Ankush Chakrabarty, Gordon Wichern, Christopher Laughman

Comments 12 pages, accepted to ICML 2021 Workshop on Tackling Climate Change with Machine Learning

Zoo-Tuning: Adaptive Transfer from a Zoo of Models

Yang Shu, Zhi Kou, Zhangjie Cao, Jianmin Wang, Mingsheng Long

Comments Accepted by ICML 2021

SpreadsheetCoder: Formula Prediction from Semi-structured Context

Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Max Lin, Denny Zhou

Comments Published in ICML 2021

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data

Yasaman Esfandiari, Sin Yong Tan, Zhanhong Jiang, Aditya Balu, Ethan Herron, Chinmay Hegde, Soumik Sarkar

Comments ICML 2021 accepted paper

ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks

Jungmin Kwon, Jeongseop Kim, Hyunseo Park, In Kwon Choi

Comments 13 pages, 4 figures, To be published in ICML 2021

Bias-Free Scalable Gaussian Processes via Randomized Truncations

Andres Potapczynski, Luhuan Wu, Dan Biderman, Geoff Pleiss, John P. Cunningham

Journal ref 38th International Conference on Machine Learning (ICML 2021)

Learning from History for Byzantine Robust Optimization

Sai Praneeth Karimireddy, Lie He, Martin Jaggi

Comments ICML 2021. v2 contains stronger theory; v3 fixes some errors in the proof

Domain Generalization using Causal Matching

Divyat Mahajan, Shruti Tople, Amit Sharma

Comments Proceedings of the 38th International Conference on Machine Learning (ICML), PMLR 139, 2021. (Long Talk)

Robust Learning-Augmented Caching: An Experimental Study

Jakub Chłędowski, Adam Polak, Bartosz Szabucki, Konrad Zolna

Comments ICML 2021

Stabilizing Equilibrium Models by Jacobian Regularization

Shaojie Bai, Vladlen Koltun, J. Zico Kolter

Comments ICML 2021 Short Oral

Unsupervised Skill Discovery with Bottleneck Option Learning

Jaekyeom Kim, Seohong Park, Gunhee Kim

Comments Accepted to ICML 2021. Code at https://vision.snu.ac.kr/projects/ibol

Who is Responsible for Adversarial Defense?

Kishor Datta Gupta, Dipankar Dasgupta

Comments Accepted for poster presentation in ICML 2021 workshop "Challenges in Deploying and monitoring Machine Learning Systems"

Minimum sharpness: Scale-invariant parameter-robustness of neural networks

Hikaru Ibayashi, Takuo Hamaguchi, Masaaki Imaizumi

Comments 9 pages, accepted to ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

David Eriksson, Pierce I-Jen Chuang, Samuel Daulton, Peng Xia, Akshat Shrivastava, Arun Babu, Shicong Zhao, Ahmed Aly, Ganesh Venkatesh, Maximilian Balandat

Comments To Appear at the 8th ICML Workshop on Automated Machine Learning, ICML 2021

Graph Contrastive Learning Automated

Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang

Comments Supplementary materials are available at https://yyou1996.github.io/files/icml2021_graphcl_automated_supplement.pdf. ICML 2021

Regularizing towards Causal Invariance: Linear Models with Proxies

Michael Oberst, Nikolaj Thams, Jonas Peters, David Sontag

Comments ICML 2021 (to appear)

Representational aspects of depth and conditioning in normalizing flows

Frederic Koehler, Viraj Mehta, Andrej Risteski

Comments Appeared in ICML 2021

On Power Laws in Deep Ensembles

Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, Dmitry Vetrov

Comments Published in NeurIPS 2020 and Workshop on Uncertainty and Robustness in Deep Learning at ICML 2020

Learning and Planning in Average-Reward Markov Decision Processes

Yi Wan, Abhishek Naik, Richard S. Sutton

Comments In Proceedings of ICML 2021

Private Adaptive Gradient Methods for Convex Optimization

Hilal Asi, John Duchi, Alireza Fallah, Omid Javidbakht, Kunal Talwar

Comments To appear in 38th International Conference on Machine Learning (ICML 2021)