On the Convergence of Nested Decentralized Gradient Methods With Multiple Consensus and Gradient Steps

In this paper, we consider minimizing a sum of local convex objective functions in a distributed setting, where the cost of communication and/or computation can be expensive. We extend and generalize the analysis for a class of nested gradient-based distributed algorithms [NEAR-DGD, (Berahas et al....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on signal processing 2021, Vol.69, p.4192-4203
Hauptverfasser:	Berahas, Albert, Bollapragada, Raghu, Wei, Ermin
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms communication Convergence Convex functions Distributed optimization Eigenvalues and eigenfunctions Exact solutions Iterative methods Linear programming network optimization Optimization optimization algorithms Quadratic equations Signal processing algorithms Symmetric matrices
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!