Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization

We consider the problem of minimizing composite functions of the form f ( g ( x ) ) + h ( x ) , where  f and  h are convex functions (which can be nonsmooth) and g is a smooth vector mapping. In addition, we assume that g is the average of finite number of component mappings or the expectation over...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mathematical programming Jg. 195; H. 1-2; S. 649 - 691
Hauptverfasser: Zhang, Junyu, Xiao, Lin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2022
Springer
Springer Nature B.V
Schlagworte:
ISSN:0025-5610, 1436-4646
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We consider the problem of minimizing composite functions of the form f ( g ( x ) ) + h ( x ) , where  f and  h are convex functions (which can be nonsmooth) and g is a smooth vector mapping. In addition, we assume that g is the average of finite number of component mappings or the expectation over a family of random component mappings. We propose a class of stochastic variance-reduced prox-linear algorithms for solving such problems and bound their sample complexities for finding an ϵ -stationary point in terms of the total number of evaluations of the component mappings and their Jacobians. When  g is a finite average of  N components, we obtain sample complexity O ( N + N 4 / 5 ϵ - 1 ) for both mapping and Jacobian evaluations. When g is a general expectation, we obtain sample complexities of O ( ϵ - 5 / 2 ) and O ( ϵ - 3 / 2 ) for component mappings and their Jacobians respectively. If in addition  f is smooth, then improved sample complexities of O ( N + N 1 / 2 ϵ - 1 ) and O ( ϵ - 3 / 2 ) are derived for g being a finite average and a general expectation respectively, for both component mapping and Jacobian evaluations.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0025-5610
1436-4646
DOI:10.1007/s10107-021-01709-z