ICML

Mitigating Sampling Bias and Improving Robustness in Active Learning

Ranganath Krishnan, Alok Sinha, Nilesh Ahuja, Mahesh Subedar, Omesh Tickoo, Ravi Iyer

Comments Human in the Loop Learning workshop at International Conference on Machine Learning (ICML 2021)

State Relevance for Off-Policy Evaluation

Simon P. Shen, Yecheng Jason Ma, Omer Gottesman, Finale Doshi-Velez

Comments ICML 2021

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9537-9546, 2021

No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets

Fahim Tajwar, Ananya Kumar, Sang Michael Xie, Percy Liang

Comments ICML Workshop on Uncertainty & Robustness in Deep Learning, 2021

Stochastic Iterative Graph Matching

Linfeng Liu, Michael C. Hughes, Soha Hassoun, Li-Ping Liu

Comments ICML 2021

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Berfin Şimşek, François Ged, Arthur Jacot, Francesco Spadaro, Clément Hongler, Wulfram Gerstner, Johanni Brea

Comments 29 pages, 12 figures, ICML 2021

Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks

George Dasoulas, Kevin Scaman, Aladin Virmaux

Comments 18 pages. Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021. Copyright 2021 by the author(s)

Fairness of Exposure in Stochastic Bandits

Lequn Wang, Yiwei Bai, Wen Sun, Thorsten Joachims

Comments 29 pages, 10 figures, ICML 2021

Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

Justin Bui, Robert J. Marks

Comments 10 Pages, 25 References, 10 Figures, 5 Tables

Journal ref 17th International Conference on Machine Learning and Data Mining, MLDM 2021, New York, USA, July 18-22, 2021 Proceedings, Pages 171-181

Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity

Zhuoning Yuan, Zhishuai Guo, Yi Xu, Yiming Ying, Tianbao Yang

Comments Accepted by ICML2021. Code is available in https://github.com/Optimization-AI/ICML2021_FedDeepAUC_CODASCA, which is a part of our open-sourced library LibAUC (www.libauc.org)

Journal ref International Conference on Machine Learning (ICML 2021)

Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition

Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren, Ben Glocker

Comments Presented at the ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning

A Study of Joint Graph Inference and Forecasting

Daniel Zügner, François-Xavier Aubet, Victor Garcia Satorras, Tim Januschowski, Stephan Günnemann, Jan Gasthaus

Comments Published at the ICML 2021 Time Series Workshop

Estimation of Corporate Greenhouse Gas Emissions via Machine Learning

You Han, Achintya Gopal, Liwen Ouyang, Aaron Key

Comments Accepted for the Tackling Climate Change with Machine Learning Workshop at ICML 2021

Provably efficient RL with Rich Observations via Latent State Decoding

Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford

Comments The ICML 2019 version omitted the second constraint on $ε$ in Theorem 4.1. We thank Yonathan Efroni for calling this to our attention

Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity

Ryan Henderson, Djork-Arné Clevert, Floriane Montanari

Comments Fixed typo and reference

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4203-4213, 2021

Predicting Mood Disorder Symptoms with Remotely Collected Videos Using an Interpretable Multimodal Dynamic Attention Fusion Network

Tathagata Banerjee, Matthew Kollada, Pablo Gersberg, Oscar Rodriguez, Jane Tiller, Andrew E Jaffe, John Reynders

Comments 8 pages, 3 figures, Published in the Computational Approaches to Mental Health Workshop of the International Conference on Machine Learning 2021, accepted-papers" target="_blank" rel="noopener">https://sites.google.com/view/ca2mh/accepted-papers

Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques

Ashly Lau, Jonathan Passerat-Palmbach

Comments Accepted to the ICML 2021 Theory and Practice of Differential Privacy Workshop

On Second-order Optimization Methods for Federated Learning

Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian U. Stich

Comments ICML 2021 Workshop "Beyond first-order methods in ML systems"

Spatial Domain Feature Extraction Methods for Unconstrained Handwritten Malayalam Character Recognition

Jomy John

Comments 10 Pages, 5 figures

Journal ref Two day International Conference on MACHINE LEARNING AND NEURAL INFORMATION SYSTEMS (ICMLNIS-2021)18-19 March 2021,A-3,Page 2, ISBN-13:978-93-90614-27-1

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Animashree Anandkumar

Comments International Conference on Machine Learning

Online mirror descent and dual averaging: keeping pace in the dynamic case

Huang Fang, Nicholas J. A. Harvey, Victor S. Portella, Michael P. Friedlander

Comments 27 pages main text, 37 pages in total, 1 figure. Version 2: Revision for camera-ready version of ICML 2020, with a new abstract, new discussion and acknowledgements sections, and some other minor modifications. Version 3: Technical report version of JMLR submission, with minor revisions, full proofs, and more details on the setting with composite functions

Dash: Semi-Supervised Learning with Dynamic Thresholding

Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yu-Feng Li, Baigui Sun, Hao Li, Rong Jin

Comments ICML 2021

An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation

Yan Shen, Zhanghexuan Ji, Mingchen Gao

Comments Accepted by 2020 11TH International Conference on Machine Learning in Medical Imaging (MLMI 2020)

PonderNet: Learning to Ponder

Andrea Banino, Jan Balaguer, Charles Blundell

Comments 16 pages, 2 figures, 2 tables, 8th ICML Workshop on Automated Machine Learning (2021)

Physical Reasoning Using Dynamics-Aware Models

Eltayeb Ahmed, Anton Bakhtin, Laurens van der Maaten, Rohit Girdhar

Comments ICML 2021 Workshop on Self-Supervised Learning for Reasoning and Perception; Webpage/Code: https://facebookresearch.github.io/DynamicsAware

APS: Active Pretraining with Successor Features

Hao Liu, Pieter Abbeel

Comments Appeared in ICML 2021

GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization

Yen-Hsiu Chou, Shenda Hong, Chenxi Sun, Derun Cai, Moxian Song, Hongyan Li

Comments (FL-ICML'21) International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021

DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions

Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kıcıman

Comments Presented at ICML 2021 Workshop on the Neglected Assumptions in Causal Inference(NACI)

Bilevel Optimization: Convergence Analysis and Enhanced Design

Kaiyi Ji, Junjie Yang, Yingbin Liang

Comments 29 pages, 19 figures and 2 tables. Published in ICML 2021

Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures

Martijn Gösgens, Alexey Tikhonov, Liudmila Prokhorenkova

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

CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training

Hari Prasanna Das, Ryan Tran, Japjot Singh, Yu-Wen Lin, Costas J. Spanos

Comments Workshop on Machine Learning for Data: Automated Creation,Privacy, Bias, In 38th International Conference on Machine Learning (ICML) 2021