Federated Learning via Inexact ADMM
Optimization and Control
2023-09-26 v4 Machine Learning
Abstract
One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence. Different from the widely-used gradient descent-based algorithms, in this paper, we develop an inexact alternating direction method of multipliers (ADMM), which is both computation- and communication-efficient, capable of combating the stragglers' effect, and convergent under mild conditions. Furthermore, it has a high numerical performance compared with several state-of-the-art algorithms for federated learning.
Keywords
Cite
@article{arxiv.2204.10607,
title = {Federated Learning via Inexact ADMM},
author = {Shenglong Zhou and Geoffrey Ye Li},
journal= {arXiv preprint arXiv:2204.10607},
year = {2023}
}