Gossip-based asynchronous algorithms for distributed composite optimization

The distributed composite optimization problem associated a multi-agent network is investigated in this paper. Different from conventional optimization issues, the cost function of composite optimization consists of a convex function and a regularization function (possibly nonsmooth). The gossip pro...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 616; S. 128952
Hauptverfasser: Fang, Xianju, Zhang, Baoyong, Yuan, Deming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.02.2025
Schlagworte:
Asynchronous algorithm
Composite optimization
Distributed optimization
Gossip protocol
Mirror descent
Mirror descent
Composite optimization
Distributed optimization
Asynchronous algorithm
Gossip protocol
ISSN:0925-2312
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The distributed composite optimization problem associated a multi-agent network is investigated in this paper. Different from conventional optimization issues, the cost function of composite optimization consists of a convex function and a regularization function (possibly nonsmooth). The gossip protocol is also introduced to enhance the robustness of the network, and a gossip-based distributed composite mirror descent algorithm is presented to deal with the previous problem, which adopts the asynchronous communication method. Moreover, the algorithm performance is analyzed and the theoretical results on the corresponding error bounds are obtained. Finally, the distributed logistic regression is provided as an example to validate the practicability of the proposed algorithm.
ISSN:0925-2312
DOI:10.1016/j.neucom.2024.128952