Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes

This paper considers the problem of decentralized, personalized federated learning. For centralized personalized federated learning, a penalty that measures the deviation from the local model and its average, is often added to the objective function. However, in a decentralized setting this penalty...

Full description

Bibliographic Details

Published in:	EURO Journal on Computational Optimization
Main Authors:	Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takáč, Alexander Gasnikov
Format:	Article
Language:	English
Published:	Elsevier 2022-01-01
Subjects:	Federated learning Decentralized optimization Distributed optimization Lower and upper bounds Accelerated algorithms
Online Access:	http://www.sciencedirect.com/science/article/pii/S219244062200017X