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

DOI10.1016/j.ejco.2022.100041zbMath1530.90103arXiv2107.07190OpenAlexW4295413102MaRDI QIDQ6170035

Abdurakhmon Sadiev, Aleksandr Beznosikov, Savelii Chezhegov, Rachael Tappenden, Ekaterina Borodich, A. V. Gasnikov, Martin Takáč, Darina Dvinskikh

Publication date: 12 July 2023

Published in: EURO Journal on Computational Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2107.07190

zbMATH Keywords

lower and upper boundsdecentralized optimizationdistributed optimizationfederated learningaccelerated algorithms

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear programming (90C30) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Introductory lectures on convex optimization. A basic course.
• Eigenvalues of the Laplacian of a graph^∗
• Distributed Subgradient Methods for Multi-Agent Optimization
• Advances and Open Problems in Federated Learning
• Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
• An Optimal Algorithm for Decentralized Finite-Sum Optimization
• Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
• Understanding Machine Learning
• Unnamed Item

This page was built for publication: Decentralized personalized federated learning: lower bounds and optimal algorithm for all personalization modes