Forward-reflected-backward method with variance reduction

We propose a variance reduced algorithm for solving monotone variational inequalities. Without assuming strong monotonicity, cocoercivity, or boundedness of the domain, we prove almost sure convergence of the iterates generated by the algorithm to a solution. In the monotone case, the ergodic averag...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computational optimization and applications Jg. 80; H. 2; S. 321 - 346
Hauptverfasser: Alacaoglu, Ahmet, Malitsky, Yura, Cevher, Volkan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.11.2021
Springer Nature B.V
Schlagworte:
Algorithms
Convergence
Convex and Discrete Geometry
Inclusions
Inequalities
Management Science
Mathematics
Mathematics and Statistics
Operations Research
Operations Research/Decision Theory
Optimization
Statistics
Finite-sum structure
Monotone inclusions
Stochastic variance reduction
Variational inequalities
Saddle point problems
ISSN:0926-6003, 1573-2894, 1573-2894
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a variance reduced algorithm for solving monotone variational inequalities. Without assuming strong monotonicity, cocoercivity, or boundedness of the domain, we prove almost sure convergence of the iterates generated by the algorithm to a solution. In the monotone case, the ergodic average converges with the optimal O (1/ k ) rate of convergence. When strong monotonicity is assumed, the algorithm converges linearly, without requiring the knowledge of strong monotonicity constant. We finalize with extensions and applications of our results to monotone inclusions, a class of non-monotone variational inequalities and Bregman projections.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0926-6003
1573-2894
1573-2894
DOI:10.1007/s10589-021-00305-3