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 Filip Hanzely

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

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques


Feb 19, 2021
Filip Hanzely, Boxin Zhao, Mladen Kolar

* 41 pages, 4 figures 

  Access Paper or Ask Questions

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization


Feb 14, 2021
Mher Safaryan, Filip Hanzely, Peter Richtárik

* 59 pages, 5 figues, 6 tables 

  Access Paper or Ask Questions

Local SGD: Unified Theory and New Efficient Methods


Nov 03, 2020
Eduard Gorbunov, Filip Hanzely, Peter Richtárik

* 79 pages, 6 figures, 7 tables 

  Access Paper or Ask Questions

Lower Bounds and Optimal Algorithms for Personalized Federated Learning


Oct 05, 2020
Filip Hanzely, Slavom├şr Hanzely, Samuel Horv├íth, Peter Richt├írik

* NeurIPS 2020 

  Access Paper or Ask Questions

Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters


Aug 26, 2020
Filip Hanzely

* PhD thesis, 425 pages, 75 figures 

  Access Paper or Ask Questions

Stochastic Subspace Cubic Newton Method


Feb 21, 2020
Filip Hanzely, Nikita Doikov, Peter Richtárik, Yurii Nesterov

* 29 pages, 5 figures, 1 table, 1 algorithm 

  Access Paper or Ask Questions

Federated Learning of a Mixture of Global and Local Models


Feb 14, 2020
Filip Hanzely, Peter Richtárik

* 43 pages, 8 algorithms, 6 figures, 1 table (minor formatting changes compared to the previous version) 

  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

Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit


May 28, 2019
Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik


  Access Paper or Ask Questions

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods


May 27, 2019
Filip Hanzely, Peter Richtárik

* 56 pages, 6 figures, 3 tables 

  Access Paper or Ask Questions

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent


May 27, 2019
Eduard Gorbunov, Filip Hanzely, Peter Richtárik

* 38 pages, 4 figures, 2 tables 

  Access Paper or Ask Questions

99% of Parallel Optimization is Inevitably a Waste of Time


Jan 27, 2019
Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

* 32 pages, 6 algorithms, 7 theorems, 12 figures 

  Access Paper or Ask Questions

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion


Jan 27, 2019
Filip Hanzely, Jakub Kone─Źn├Ż, Nicolas Loizou, Peter Richt├írik, Dmitry Grishchenko

* NeurIPS 2018, Privacy Preserving Machine Learning Workshop (camera ready version). The full-length paper, which includes a number of additional algorithms and results (including proofs of statements and experiments), is available in arXiv:1706.07636 

  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

A Nonconvex Projection Method for Robust PCA


May 21, 2018
Aritra Dutta, Filip Hanzely, Peter Richtárik


  Access Paper or Ask Questions