ICML

Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup

Jang-Hyun Kim, Wonho Choo, Hyun Oh Song

Comments Published at ICML 2020

Concept Bottleneck Models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

Comments Edited for clarity from the ICML 2020 version

When are Non-Parametric Methods Robust?

Robi Bhattacharjee, Kamalika Chaudhuri

Comments accepted to ICML 2020

On Implicit Regularization in $β$-VAEs

Abhishek Kumar, Ben Poole

Comments ICML 2020; Final version, including appendix

Bayesian Active Learning With Abstention Feedbacks

Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu, Vu Dinh, Binh Nguyen

Comments Poster presented at 2019 ICML Workshop on Human in the Loop Learning 2019 (non-archival). arXiv admin note: substantial text overlap with arXiv:1705.08481

Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations

Tri Dao, Albert Gu, Matthew Eichhorn, Atri Rudra, Christopher Ré

Comments International Conference on Machine Learning (ICML) 2019

Understanding Black-box Predictions via Influence Functions

Pang Wei Koh, Percy Liang

Comments International Conference on Machine Learning, 2017. (This version adds more historical references and fixes typos.)

Parametric Gaussian Process Regressors

Martin Jankowiak, Geoff Pleiss, Jacob R. Gardner

Comments 17 pages, 10 figures; as appeared in ICML 2020

Journal ref International Conference on Machine Learning, pp. 4702-4712. PMLR, 2020

Unbiased Gradient Estimation for Distributionally Robust Learning

Soumyadip Ghosh, Mark Squillante

Comments ICML 2020, AISTATS 2021 submission

Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection

Teguh Budianto, Tomohiro Nakai, Kazunori Imoto, Takahiro Takimoto, Kosuke Haruki

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

Inexact Tensor Methods with Dynamic Accuracies

Nikita Doikov, Yurii Nesterov

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2577-2586, 2020

ResiliNet: Failure-Resilient Inference in Distributed Neural Networks

Ashkan Yousefpour, Brian Q. Nguyen, Siddartha Devic, Guanhua Wang, Aboudy Kreidieh, Hans Lobel, Alexandre M. Bayen, Jason P. Jue

Comments Accepted in FL-ICML 2020 (International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020). Added FAQ to the end of the paper

On Contrastive Learning for Likelihood-free Inference

Conor Durkan, Iain Murray, George Papamakarios

Comments Appeared at ICML 2020

Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences

Daniel S. Brown, Russell Coleman, Ravi Srinivasan, Scott Niekum

Comments In proceedings ICML 2020

The Buckley-Osthus model and the block preferential attachment model: statistical analysis and application

Xin Guo, Fengmin Tang, Wenpin Tang

Comments 12 pages, 2 figures, 4 tables. This paper is published by http://proceedings.mlr.press/v119/tang20b.html

Journal ref Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 9377-9386

Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural Networks

Arijit Sehanobish, Neal G. Ravindra, David van Dijk

Comments To appear at AAAI'21. Previous version (v2) accepted as a spotlight talk at ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+) and recipient of best paper award for Covid-19 applications. Significant improvements over v2

DeepGamble: Towards unlocking real-time player intelligence using multi-layer instance segmentation and attribute detection

Danish Syed, Naman Gandhi, Arushi Arora, Nilesh Kadam

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

Mean Field Multi-Agent Reinforcement Learning

Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, Jun Wang

Comments ICML 2018 (Full paper + Long talk)

Tensor denoising and completion based on ordinal observations

Chanwoo Lee, Miaoyan Wang

Comments 35 pages, 6 figures

Journal ref Proceedings of the 37th International Conference on Machine Learning(ICML), 2020

Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients

Lukas Balles, Philipp Hennig

Comments Presented at the 35th International Conference on Machine Learning (ICML), 2018

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing

Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney

Comments This paper appears in the Proceedings of the 37th International Conference on Machine Learning, pp. 2803--2813, 2020

Learning with Bounded Instance- and Label-dependent Label Noise

Jiacheng Cheng, Tongliang Liu, Kotagiri Ramamohanarao, Dacheng Tao

Comments Published in the International Conference on Machine Learning (ICML), 2020

Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting

Niccolò Dalmasso, Rafael Izbicki, Ann B. Lee

Comments 20 pages, 8 figures, 6 tables, 4 algorithm boxes

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2323-2334, 2020

Randomized Block-Diagonal Preconditioning for Parallel Learning

Celestine Mendler-Dünner, Aurelien Lucchi

Comments improvement in Theorem 3 compared to ICML 2020 version

Journal ref PMLR 119:6841-6851 (2020)

BoXHED: Boosted eXact Hazard Estimator with Dynamic covariates

Xiaochen Wang, Arash Pakbin, Bobak J. Mortazavi, Hongyu Zhao, Donald K. K. Lee

Comments 10 pages, 3 figures, 5 tables

Journal ref ICML 9973-9982 (2020)

Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE

Juntang Zhuang, Nicha Dvornek, Xiaoxiao Li, Sekhar Tatikonda, Xenophon Papademetris, James Duncan

Journal ref https://proceedings.icml.cc/static/paper_files/icml/2020/917-Paper.pdf

A Novel index-based multidimensional data organization model that enhances the predictability of the machine learning algorithms

Mahbubur Rahman

Journal ref International Conference on Machine Learning Techniques and NLP (MLNLP 2020), Volume 10, Number 12, October 2020, ISBN : 978-1-925953-26-8

Heuristic-Based Weak Learning for Automated Decision-Making

Ryan Steed, Benjamin Williams

Comments 5 pages, 3 figures. Camera-ready version for Participatory Approaches to Machine Learning @ ICML 2020. Last updated Dec. 2020: fixed bug in Figure 3 - "always intervene" heuristic should be "never intervene."

On The Power of Curriculum Learning in Training Deep Networks

Guy Hacohen, Daphna Weinshall

Comments In proceedings, ICML 2019

Journal ref Proc. ICML, 2019

Information Theory in Density Destructors

J. Emmanuel Johnson, Valero Laparra, Gustau Camps-Valls, Raul Santos-Rodríguez, Jesús Malo

Comments Accepted at the Workshop on Invertible Neural Nets and Normalizing Flows, ICML 2019