Federated learning

Better Methods and Theory for Federated Learning: Compression, Client Selection, and Heterogeneity

Samuel Horváth, Ph.D. Student, Statistics

Jun 27, 18:00 - 20:00

B5 L5 R5209

Federated learning Optimization for Machine Learning

Federated learning (FL) is an emerging machine learning paradigm involving multiple clients, e.g., mobile phone devices, with an incentive to collaborate in solving a machine learning problem coordinated by a central server. FL was proposed in 2016 by Konecny et al. and McMahan et al. as a viable privacy-preserving alternative to traditional centralized machine learning since, by construction, the training data points are decentralized and never transferred by the clients to a central server. Therefore, to a certain degree, FL mitigates the privacy risks associated with centralized data collection. Unfortunately, optimization for FL faces several specific issues that centralized optimization usually does not need to handle. In this thesis, we identify several of these challenges and propose new methods and algorithms to address them, with the ultimate goal of enabling practical FL solutions supported with mathematically rigorous guarantees.

Laurent Condat

Senior Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering

optimization Federated learning Distributed algorithms Signal and Image Processing

I am a senior researcher working in optimization, in the group of Prof. Peter Richtárik.

Konstantin Burlachenko

Ph.D. Student, Computer Science

Federated learning Optimization for Machine Learning High Performance Computing software development

Konstantin Burlachenko is a Ph.D. candidate at the KAUST Optimization and Machine Learning Lab under the supervision of Professor Peter Richtarik.

Grigorii Malinovskii

Ph.D. Student, Computer Science

machine learning convex optimization Federated learning

I am a PhD student in Applied Mathematics and Computational Science at King Abdullah University of Science and Technology, advised by Prof. Peter Richtárik, working on optimization theory and its applications in Machine Learning. My hobbies include drums, fitness, martial arts, football, and basketball.

Egor Shulgin

Ph.D. Student, Computer Science

machine learning optimization Federated learning

Egor Shulgin is a CS student in the MS/Ph.D. program under the supervision of Professor Peter Richtarik at the Visual Computing Center (VCC) at the King Abdullah University of Science and Technology (KAUST), Saudi Arabia. Education and Early Career Egor obtained his bachelor's degree in Applied Mathematics, Physics, and Computer Science from the Moscow Institute of Physics and Technology (MIPT) in 2019. He first came to KAUST for a research visit in 2019. Later, he joined Prof. Peter Richtarik's group as a MS/Ph.D. student. In 2021 Egor did a research internship with Distributed AI team at the