ICML

Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering

Romain Couillet, Florent Chatelain, Nicolas Le Bihan

Comments 24 pages (10 for the core paper, 14 for the proofs in supplementary materials) , 10 figures. Final version to be published in ICML 2021 proceedings

CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients

Dani Kiyasseh, Tingting Zhu, David A. Clifton

Comments Accepted to ICML 2021

Locally Private k-Means in One Round

Alisa Chang, Badih Ghazi, Ravi Kumar, Pasin Manurangsi

Comments 35 pages. To appear in ICML'21

Whitening for Self-Supervised Representation Learning

Aleksandr Ermolov, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe

Comments ICML 2021

Delving into Deep Imbalanced Regression

Yuzhe Yang, Kaiwen Zha, Ying-Cong Chen, Hao Wang, Dina Katabi

Comments ICML 2021 (Long Oral)

Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces

Ankit Singh Rawat, Aditya Krishna Menon, Wittawat Jitkrittum, Sadeep Jayasumana, Felix X. Yu, Sashank Reddi, Sanjiv Kumar

Comments To appear in ICML 2021

Cyclically Equivariant Neural Decoders for Cyclic Codes

Xiangyu Chen, Min Ye

Comments Accepted for long presentation at ICML 2021. Code available at https://github.com/cyclicallyneuraldecoder/CyclicallyEquivariantNeuralDecoders

GLSearch: Maximum Common Subgraph Detection via Learning to Search

Yunsheng Bai, Derek Xu, Yizhou Sun, Wei Wang

Comments Accepted by ICML 2021

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis

Baihe Huang, Xiaoxiao Li, Zhao Song, Xin Yang

Comments ICML 2021

Estimation and Quantization of Expected Persistence Diagrams

Vincent Divol, Théo Lacombe

Journal ref International Conference on Machine Learning, Jul 2021, Virtual Conference, France

Value Iteration in Continuous Actions, States and Time

Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg

Comments Accepted at International Conference on Machine Learning (ICML) 2021

Neural SDEs as Infinite-Dimensional GANs

Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry Lyons

Comments Published at ICML 2021

"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms

Patrick Kidger, Ricky T. Q. Chen, Terry Lyons

Comments Published at ICML 2021

Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

Yuzhou Chen, Ignacio Segovia-Dominguez, Yulia R. Gel

Comments Accepted at the International Conference on Machine Learning (ICML) 2021

Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics

Greg Yang, Etai Littwin

Comments ICML 2021

On the Convergence of SGD with Biased Gradients

Ahmad Ajalloeian, Sebastian U. Stich

Comments Accepted to ICML 2020 Workshop "Beyond First Order Methods in ML Systems", updated 2021

Coded Computing for Federated Learning at the Edge

Saurav Prakash, Sagar Dhakal, Mustafa Akdeniz, A. Salman Avestimehr, Nageen Himayat

Comments Work accepted for presentation at the International Workshop on Federated Learning for User Privacy and Data Confidentiality, in Conjunction with ICML 2020 (FL-ICML'20). This work was part of Saurav Prakash's internship projects at Intel. arXiv admin note: text overlap with arXiv:2011.06223

Zeno++: Robust Fully Asynchronous SGD

Cong Xie, Sanmi Koyejo, Indranil Gupta

Comments ICML version with some additional remarks related to the acceptance rate of Byzantine validation, and also with the full version of error bounds in the theorems

In the Danger Zone: U-Net Driven Quantile Regression can Predict High-risk SARS-CoV-2 Regions via Pollutant Particulate Matter and Satellite Imagery

Jacquelyn Shelton, Przemyslaw Polewski, Wei Yao

Comments accepted for ICML 2020 Workshop on Healthcare Systems, Population Health, and the Role of Health-Tech

FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimize

Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How

Comments Accepted to ICML 2020 Workshop Theoretical Foundations of RL; Accepted to ICRA 2021

EEC: Learning to Encode and Regenerate Images for Continual Learning

Ali Ayub, Alan R. Wagner

Comments Added link to the code in the paper. A preliminary version of this work was presented at ICML 2020 Workshop on Lifelong Machine Learning: arXiv:2007.06637

Journal ref International Conference on Learning Representations (ICLR) 2021

Laplacian Regularized Few-Shot Learning

Imtiaz Masud Ziko, Jose Dolz, Eric Granger, Ismail Ben Ayed

Comments ICML 2020 paper

PowerNorm: Rethinking Batch Normalization in Transformers

Sheng Shen, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer

Journal ref ICML 2020

PyHessian: Neural Networks Through the Lens of the Hessian

Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney

Journal ref IEEE BigData 2020 (and ICML Workshop 2020)

Coarse- and fine-scale geometric information content of Multiclass Classification and implied Data-driven Intelligence

Fushing Hsieh, Xiaodong Wang

Comments 15 pages, 5 figures

Journal ref In Proceedings of the 16th International Conference on Machine Learning and Data Mining, MLDM 2020, July 20-21, 2020, Amsterdam, The Netherlands, pp 171-184

Tightening Exploration in Upper Confidence Reinforcement Learning

Hippolyte Bourel, Odalric-Ambrym Maillard, Mohammad Sadegh Talebi

Comments Appeared in Proceedings of the 27th International Conference on Machine Learning (ICML 2020). This is an improved post-proceeding version correcting minor errors

On Analyzing Churn Prediction in Mobile Games

Kihoon Jang, Junwhan Kim, Byunggu Yu

Comments 8 pages, 10 figures, 2021 6th International Conference on Machine Learning Technologies

A Graph VAE and Graph Transformer Approach to Generating Molecular Graphs

Joshua Mitton, Hans M. Senn, Klaas Wynne, Roderick Murray-Smith

Comments Graph Representation Learning and Beyond (GRL+) (ICML 2020)

SCAFFOLD: Stochastic Controlled Averaging for Federated Learning

Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh

Comments v2 contains analysis of FedAvg, non-convex rates of Scaffold, and experimental evaluation. v3 fixes typos, ICML version. v4 slightly improves rate of SCAFFOLD for general convex functions

Deep PQR: Solving Inverse Reinforcement Learning using Anchor Actions

Sinong Geng, Houssam Nassif, Carlos A. Manzanares, A. Max Reppen, Ronnie Sircar

Journal ref In Proceedings of the 37th ICML, Vienna, Austria, PMLR 119, pp. 3431-3441, 2020