Journals
Resources
About Us
Open Access

Review of Mathematical Optimization in Federated Learning

Review of Mathematical Optimization in Federated Learning

Year:    2025

Author:    Shusen Yang, Fangyuan Zhao, Zihao Zhou, Liang Shi, Xuebin Ren, Zongben Xu

CSIAM Transactions on Applied Mathematics, Vol. 6 (2025), Iss. 2 : pp. 207–249

Abstract

Federated learning (FL) has been becoming a popular interdisciplinary research area in both applied mathematics and information sciences. Mathematically, FL aims to collaboratively optimize aggregate objective functions over distributed datasets while satisfying a variety of privacy and system constraints. Different from conventional distributed optimization methods, FL needs to address several specific issues (e.g. non-i.i.d. data and differential private noises), which pose a set of new challenges in the problem formulation, algorithm design, and convergence analysis. In this paper, we will systematically review existing FL optimization research including their assumptions, formulations, methods, and theoretical results. Potential future directions are also discussed.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/csiam-am.SO-2024-0023

CSIAM Transactions on Applied Mathematics, Vol. 6 (2025), Iss. 2 : pp. 207–249

Published online:    2025-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    43

Keywords:    Federated learning distributed optimization convergence analysis error bounds.

Author Details

Shusen Yang

Fangyuan Zhao

Zihao Zhou

Liang Shi

Xuebin Ren

Zongben Xu

  1. A Survey of Differential Privacy Techniques for Federated Learning

    Xin, Wang

    Jiaqian, Li

    Xueshuang, Ding

    Haoji, Zhang

    Lianshan, Sun

    IEEE Access, Vol. 13 (2025), Iss. P.6539

    https://doi.org/10.1109/ACCESS.2024.3523909 [Citations: 1]