Distributed constrained optimization over unbalanced graphs and delayed gradient

In this paper, we investigate a distributed constrained optimization problem subject to convex, closed, and nonidentical set constraints over unbalanced graphs, where each agent has local access to its strongly convex objective function and collaborates, minimizing the sum of these functions. To add...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the Franklin Institute Jg. 362; H. 2; S. 107466
Hauptverfasser: Huang, Qing, Fan, Yuan, Cheng, Songsong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.01.2025
Schlagworte:
Convergence
Distributed optimization
Gradient delay
Nonidentical constraints
Unbalanced graphs
Distributed optimization
Nonidentical constraints
Gradient delay
Unbalanced graphs
Convergence
ISSN:0016-0032
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we investigate a distributed constrained optimization problem subject to convex, closed, and nonidentical set constraints over unbalanced graphs, where each agent has local access to its strongly convex objective function and collaborates, minimizing the sum of these functions. To address this problem, we design a distributed projected delayed gradient algorithm by using the available delayed gradient information, which removes dependence on the current gradient information and increases iteration efficiency. Moreover, to improve communication robustness, the algorithm is only based on a row stochastic weight matrix and achieves an O(1/T) convergence rate for a non-negative and diminishing step size. Finally, we present a numerical example to verify the effectiveness of the algorithm.
ISSN:0016-0032
DOI:10.1016/j.jfranklin.2024.107466