Filip Hanzely

Assistant Professor, Toyota Technological Institute at Chicago

Joined

September 2019

Names

Filip Hanzely (Preferred)

Emails

****@gmail.com (Confirmed)

****@kaust.edu.sa (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Assistant Professor

Toyota Technological Institute at Chicago (ttic.edu)

2020 – Present

PhD student

KAUST (kaust.edu.sa)

2017 – 2020

MS student

University of Edinburgh (ed.ac.uk)

2016 – 2017

Undergrad student

Comenius University (uniba.sk)

2013 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Peter Richtarik

2016 – Present

Expertise

optimization

machine learning

2016 – Present

Publications

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
Filip Hanzely, Boxin Zhao, mladen kolar
- Accepted by TMLR
- Readers: Everyone
Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization
Mher Safaryan, Filip Hanzely, Peter Richtárik
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Local SGD: Unified Theory and New Efficient Methods
Eduard Gorbunov, Filip Hanzely, Peter Richtarik
- 06 May 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
Federated Learning of a Mixture of Global and Local Models
Filip Hanzely, Peter Richtarik
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
A Nonconvex Projection Method for Robust PCA.
Aritra Dutta, Filip Hanzely, Peter Richtárik
- 2019 (modified: 10 Nov 2022)
- AAAI2019
- Readers: Everyone
SEGA: Variance Reduction via Gradient Sketching
Filip Hanzely, Konstantin Mishchenko, Peter Richtárik
- 2018 (modified: 11 Nov 2022)
- NeurIPS 2018
- Readers: Everyone
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization
Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
- 2018 (modified: 11 Nov 2022)
- NeurIPS 2018
- Readers: Everyone

Filip Hanzely

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

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

Local SGD: Unified Theory and New Efficient Methods

Federated Learning of a Mixture of Global and Local Models

A Nonconvex Projection Method for Robust PCA.

SEGA: Variance Reduction via Gradient Sketching

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

Co-Authors