Proximal quasi-Newton methods for regularized convex optimization with linear and accelerated sublinear convergence rates

A general, inexact, efficient proximal quasi-Newton algorithm for composite optimization problems has been proposed by Scheinberg and Tang (Math Program 160:495–529, 2016 ) and a sublinear global convergence rate has been established. In this paper, we analyze the global convergence rate of this met...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computational optimization and applications 2018-04, Vol.69 (3), p.597-627
Hauptverfasser:	Ghanbari, Hiva, Scheinberg, Katya
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Computational geometry Convergence Convex and Discrete Geometry Convexity Economic models Management Science Mathematics Mathematics and Statistics Newton methods Nonlinear programming Operations Research Operations Research/Decision Theory Optimization Statistics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!