A randomized method for handling a difficult function in a convex optimization problem, motivated by probabilistic programming

We propose a randomized gradient method for handling a convex function whose gradient computation is demanding. The method bears a resemblance to the stochastic approximation family. But in contrast to stochastic approximation, the present method builds a model problem. The approach is adapted to pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Annals of operations research 2019, p.1-32
Hauptverfasser: Fábián, Csaba I., Csizmás, Edit, Drenyovszki, Rajmund, Vajnai, Tibor, Kovács, Lóránt, Szántai, Tamás
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a randomized gradient method for handling a convex function whose gradient computation is demanding. The method bears a resemblance to the stochastic approximation family. But in contrast to stochastic approximation, the present method builds a model problem. The approach is adapted to probability maximization and probabilistic constrained problems. We discuss simulation procedures for gradient estimation.
ISSN:0254-5330
1572-9338
DOI:10.1007/s10479-019-03143-z