DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jongho, Xu, Jinchao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914636279840768
author Park, Jongho
Xu, Jinchao
author_facet Park, Jongho
Xu, Jinchao
contents We propose a new training algorithm, named DualFL (Dualized Federated Learning), for solving distributed optimization problems in federated learning. DualFL achieves communication acceleration for very general convex cost functions, thereby providing a solution to an open theoretical problem in federated learning concerning cost functions that may not be smooth nor strongly convex. We provide a detailed analysis for the local iteration complexity of DualFL to ensure the overall computational efficiency of DualFL. Furthermore, we introduce a completely new approach for the convergence analysis of federated learning based on a dual formulation. This new technique enables concise and elegant analysis, which contrasts the complex calculations used in existing literature on convergence of federated learning algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2305_10294
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime
Park, Jongho
Xu, Jinchao
Machine Learning
Optimization and Control
68W15, 90C46, 90C25
We propose a new training algorithm, named DualFL (Dualized Federated Learning), for solving distributed optimization problems in federated learning. DualFL achieves communication acceleration for very general convex cost functions, thereby providing a solution to an open theoretical problem in federated learning concerning cost functions that may not be smooth nor strongly convex. We provide a detailed analysis for the local iteration complexity of DualFL to ensure the overall computational efficiency of DualFL. Furthermore, we introduce a completely new approach for the convergence analysis of federated learning based on a dual formulation. This new technique enables concise and elegant analysis, which contrasts the complex calculations used in existing literature on convergence of federated learning algorithms.
title DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime
topic Machine Learning
Optimization and Control
68W15, 90C46, 90C25
url https://arxiv.org/abs/2305.10294