Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Peter Richtarik

A Field Guide to Federated Optimization


Jul 14, 2021
Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Aguera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horvath, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecny, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtarik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu


  Access Paper or Ask Questions

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!


Nov 03, 2020
Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtarik, Sebastian U. Stich


  Access Paper or Ask Questions

Optimal Client Sampling for Federated Learning


Oct 26, 2020
Wenlin Chen, Samuel Horvath, Peter Richtarik

* 11 pages, 10 pages of Appendix, 6 Figures, 3 algorithms, code available: https://github.com/SamuelHorvath/FL-optimal-client-sampling 

  Access Paper or Ask Questions

Variance-Reduced Methods for Machine Learning


Oct 02, 2020
Robert M. Gower, Mark Schmidt, Francis Bach, Peter Richtarik

* 16 pages, 7 figures, 1 table 

  Access Paper or Ask Questions

Adaptive Learning of the Optimal Mini-Batch Size of SGD


May 03, 2020
Motasem Alfarra, Slavomir Hanzely, Alyazeed Albasyoni, Bernard Ghanem, Peter Richtarik

* 17 pages, 45 figures 

  Access Paper or Ask Questions

Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms


Apr 03, 2020
Adil Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtarik


  Access Paper or Ask Questions

From Local SGD to Local Fixed Point Methods for Federated Learning


Apr 03, 2020
Grigory Malinovsky, Dmitry Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtarik


  Access Paper or Ask Questions

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems


Feb 11, 2020
Filip Hanzely, Dmitry Kovalev, Peter Richtarik

* 30 pages, 8 figures 

  Access Paper or Ask Questions

Natural Compression for Distributed Deep Learning


May 27, 2019
Samuel Horvath, Chen-Yu Ho, Ludovit Horvath, Atal Narayan Sahu, Marco Canini, Peter Richtarik

* 8 pages, 20 pages of Appendix, 6 Tables, 14 Figures, 1 Algorithm, 10 Theorems, 9 Lemmas, 5 Definitions 

  Access Paper or Ask Questions

SGD: General Analysis and Improved Rates


Jan 27, 2019
Robert Mansel Gower, Nicolas Loizou, Xun Qian, Alibek Sailanbayev, Egor Shulgin, Peter Richtarik

* 22 pages 

  Access Paper or Ask Questions

Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop


Jan 24, 2019
Dmitry Kovalev, Samuel Horvath, Peter Richtarik

* 14 pages, 2 algorithms, 9 lemmas, 2 theorems, 4 figures 

  Access Paper or Ask Questions

SEGA: Variance Reduction via Gradient Sketching


Oct 18, 2018
Filip Hanzely, Konstantin Mishchenko, Peter Richtarik

* Accepted to the NIPS conference 

  Access Paper or Ask Questions

Weighted Low-Rank Approximation of Matrices and Background Modeling


Apr 15, 2018
Aritra Dutta, Xin Li, Peter Richtarik

* arXiv admin note: text overlap with arXiv:1707.00281 

  Access Paper or Ask Questions

Online and Batch Supervised Background Estimation via L1 Regression


Nov 23, 2017
Aritra Dutta, Peter Richtarik


  Access Paper or Ask Questions

Matrix Completion under Interval Uncertainty


Apr 01, 2016
Jakub Marecek, Peter Richtarik, Martin Takac

* European Journal on Operational Research (2017) 256 (1): 35-43 

  Access Paper or Ask Questions

Separable Approximations and Decomposition Methods for the Augmented Lagrangian


Aug 30, 2013
Rachael Tappenden, Peter Richtarik, Burak Buke

* 28 pages, 6 algorithms, 2 figures 

  Access Paper or Ask Questions