PMGT-VR: a Decentralized Proximal-gradient Algorithmic Framework with Variance Reduction

This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed fr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence Jg. 48; H. 1; S. 1 - 12
Hauptverfasser:	Ye, Haishan, Xiong, Wei, Zhang, Tong
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 05.09.2025
Schlagworte:	Complexity theory Convergence Decentralized optimization Loss measurement Network topology Optimization proximal-gradient Servers Symmetric matrices Topology Training variance reduction Vectors
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!