Non-convex composite federated learning with heterogeneous data

DOI10.1016/J.AUTOMATICA.2025.112695MaRDI QIDQ6884486zbMATH OpenFDO

Authors Jiaojiao Zhang, Jiang Hu, Mikael Johansson

Publication date 15 December 2025

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2025.112695

zbMATH Keywords

heterogeneous datalocal updatenon-convex composite federated learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonconvex programming, global optimization (90C26)

Cites work

• A family of inexact SQA methods for non-smooth convex minimization with provable convergence guarantees based on the Luo-Tseng error bound property
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A strictly contractive Peaceman-Rachford splitting method for convex programming
• Decentralized nonconvex optimization with guaranteed privacy and accuracy
• Distributed networked learning with correlated data
• Distributed Networked Real-Time Learning
• Error bounds and convergence analysis of feasible descent methods: A general approach
• FedPD: a federated learning framework with adaptivity to non-IID data
• Gradient free cooperative seeking of a moving source
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
• On stochastic gradient and subgradient methods with adaptive steplength sequences
• Online optimization of switched LTI systems using continuous-time and hybrid accelerated gradient flows
• Primal-dual subgradient methods for convex problems
• Sparse linear regression from perturbed data

This page was built for publication: Non-convex composite federated learning with heterogeneous data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6884486)