ICML

Certified Robustness to Label-Flipping Attacks via Randomized Smoothing

Elan Rosenfeld, Ezra Winston, Pradeep Ravikumar, J. Zico Kolter

Comments ICML 2020

The Effects of Image Distribution and Task on Adversarial Robustness

Owen Kunhardt, Arturo Deza, Tomaso Poggio

Comments Under review at ICML 2021

SGD: General Analysis and Improved Rates

Robert Mansel Gower, Nicolas Loizou, Xun Qian, Alibek Sailanbayev, Egor Shulgin, Peter Richtarik

Comments 23 pages, 6 figures

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:5200-5209, 2019

Efficient Discretizations of Optimal Transport

Junqi Wang, Pei Wang, Patrick Shafto

Comments 17 pages, 14 figures. Submitted to ICML 2021

Healing Products of Gaussian Processes

Samuel Cohen, Rendani Mbuvha, Tshilidzi Marwala, Marc Peter Deisenroth

Comments ICML 2020

Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization

Vien V. Mai, Mikael Johansson

Comments ICML-2020

Graph-Aided Online Multi-Kernel Learning

Pouya M Ghari, Yanning Shen

Comments Preliminary results of this work have been presented in "Online Multi-Kernel Learning with Graph-Structured Feedback." P. M. Ghari, and Y. Shen, International Conference on Machine Learning (ICML), pp. 3474-3483. PMLR, July 2020

Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint

Dong Yin, Mehrdad Farajtabar, Ang Li, Nir Levine, Alex Mott

Comments Preliminary version with a different title presented at ICML Workshop on Continual Learning, 2020 (spotlight)

A Generative Model for Molecular Distance Geometry

Gregor N. C. Simm, José Miguel Hernández-Lobato

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

On the Sample Complexity of Causal Discovery and the Value of Domain Expertise

Samir Wadhwa, Roy Dong

Comments Submitted to ICML 2021

Machine Learning for Auxiliary Sources

Daniele Casati

Comments 8 pages, 12 figures, submitted to ICML 2021

Effects of Number of Filters of Convolutional Layers on Speech Recognition Model Accuracy

James Mou, Jun Li

Comments 8 pages, 9 figures, 3 tables, to be published in the Proc. of the 19th IEEE International Conference on Machine Learning and Applications, Page 971-978, 2020. DOI 10.1109/ICMLA51294.2020.00158. \c{opyright} 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, including reprinting/republishing this material for advertising purposes

Generalized Approximate Survey Propagation for High-Dimensional Estimation

Luca Saglietti, Yue M. Lu, Carlo Lucibello

Journal ref ICML 2019

VAFL: a Method of Vertical Asynchronous Federated Learning

Tianyi Chen, Xiao Jin, Yuejiao Sun, Wotao Yin

Comments FL-ICML'20: Proc. of ICML Workshop on Federated Learning for User Privacy and Data Confidentiality, July 2020

Journal ref Proc. of ICML Workshop on Federated Learning for User Privacy and Data Confidentiality, July 2020

Born-Again Tree Ensembles

Thibaut Vidal, Toni Pacheco, Maximilian Schiffer

Comments "Born-Again Tree Ensembles", proceedings of ICML 2020. The associated source code is available at: https://github.com/vidalt/BA-Trees

Journal ref Proceedings of the 37th International Conference on Machine Learning (ICML). Vol. 119, pp. 9743-9753 (2020)

Structured Prediction with Partial Labelling through the Infimum Loss

Vivien Cabannes, Alessandro Rudi, Francis Bach

Comments 8 pages for main paper, 27 with main paper, 13 figures, 3 tables

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:1230-1239, 2020

Learning Similarity Metrics for Numerical Simulations

Georg Kohl, Kiwon Um, Nils Thuerey

Comments Main paper: 9 pages, Appendix: 19 pages. Accepted at ICML 2020. Source code available at https://github.com/tum-pbs/LSIM and further information at https://ge.in.tum.de/publications/2020-lsim-kohl/

Journal ref Proceedings of Machine Learning Research 119 (2020) 5349-5360

Consistent Estimators for Learning to Defer to an Expert

Hussein Mozannar, David Sontag

Comments ICML 2020

Universal Average-Case Optimality of Polyak Momentum

Damien Scieur, Fabian Pedregosa

Comments Added references in the proof of Theorem 4.1

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

Cycle-StarNet: Bridging the gap between theory and data by leveraging large datasets

Teaghan O'Briain, Yuan-Sen Ting, Sébastien Fabbro, Kwang M. Yi, Kim Venn, Spencer Bialek

Comments 23 pages, 15 figures, 2 tables, accepted for publication on Nov 12, 2020, Nov 12. A companion 4-page preview is accepted to the ICML 2020 Machine Learning Interpretability for Scientific Discovery workshop. The code used in this study is made publicly available on github: https://github.com/teaghan/Cycle_SN

Journal ref 2021, ApJ, 906, 130

Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters

Wenhui Yu, Zheng Qin

Comments ICML 2020 paper

Deep Semi-Supervised Embedded Clustering (DSEC) for Stratification of Heart Failure Patients

Oliver Carr, Stojan Jovanovic, Luca Albergante, Fernando Andreotti, Robert Dürichen, Nadia Lipunova, Janie Baxter, Rabia Khan, Benjamin Irving

Comments 6 pages, 2 figures, HSYS workshop at ICML conference

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman

Comments 15 pages, 8 figures, ICML 2020. Website with code: https://sites.google.com/berkeley.edu/carl

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:11055-11065, 2020

Stabilizing Differentiable Architecture Search via Perturbation-based Regularization

Xiangning Chen, Cho-Jui Hsieh

Comments ICML 2020, code is available at https://github.com/xiangning-chen/SmoothDARTS

Learning deep kernels for exponential family densities

Li Wenliang, Danica J. Sutherland, Heiko Strathmann, Arthur Gretton

Journal ref Proceedings of the 36th International Conference on Machine Learning (ICML 2019), PMLR 97:6737-6746

Learning Deep Kernels for Non-Parametric Two-Sample Tests

Feng Liu, Wenkai Xu, Jie Lu, Guangquan Zhang, Arthur Gretton, Danica J. Sutherland

Journal ref Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119:6316-6326

Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

Jay Nandy, Wynne Hsu, Mong Li Lee

Comments Accepted at NeurIPS 2020 Workshop version: ICML UDL 2020, Link: accepted-papers/UDL2020-paper-134.pdf" target="_blank" rel="noopener">http://www.gatsby.ucl.ac.uk/~balaji/udl2020/accepted-papers/UDL2020-paper-134.pdf

Risk-Sensitive Compact Decision Trees for Autonomous Execution in Presence of Simulated Market Response

Svitlana Vyetrenko, Shaojie Xu

Comments Proceedings of the 36th International Conference on Machine Learning,Long Beach, California, 2019

Cyclic Boosting -- an explainable supervised machine learning algorithm

Felix Wick, Ulrich Kerzel, Michael Feindt

Comments added a discussion about causality

Journal ref 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)

Enhanced Pub/Sub Communications for Massive IoT Traffic with SARSA Reinforcement Learning

Carlos E. Arruda, Pedro F. Moraes, Nazim Agoulmine, Joberto S. B. Martins

Comments 3rd International Conference on Machine Learning for Networking - MLN 2020, Paris, 20 pages, 8 figures