Optimal Convergence Rates for Convex Distributed Optimization in Networks

This work proposes a theoretical analysis of distributed optimization of convex functions using a network of computing units. We investigate this problem under two communication schemes (centralized and decentralized) and four classical regularity assumptions: Lipschitz continuity, strong convexity,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of machine learning research 2019-01, Vol.20, p.1-31
Hauptverfasser:	Scaman, Kevin, Bach, Francis, Bubeck, Sébastien, Lee, Yin Tat, Massoulié, Laurent
Format:	Artikel
Sprache:	eng
Schlagworte:	Machine Learning Mathematics Optimization and Control Statistics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!