ANOTHER LOOK AT THE FAST ITERATIVE SHRINKAGE/THRESHOLDING ALGORITHM (FISTA)

This paper provides a new way of developing the "Fast Iterative Shrinkage/Thresholding Algorithm (FISTA)" [3] that is widely used for minimizing composite convex functions with a nonsmooth term such as the ℓ regularizer. In particular, this paper shows that FISTA corresponds to an optimize...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:SIAM journal on optimization Jg. 28; H. 1; S. 223
Hauptverfasser: Kim, Donghwan, Fessler, Jeffrey A
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 2018
ISSN:1052-6234
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper provides a new way of developing the "Fast Iterative Shrinkage/Thresholding Algorithm (FISTA)" [3] that is widely used for minimizing composite convex functions with a nonsmooth term such as the ℓ regularizer. In particular, this paper shows that FISTA corresponds to an optimized approach to accelerating the proximal gradient method with respect to a worst-case bound of the cost function. This paper then proposes a new algorithm that is derived by instead optimizing the step coefficients of the proximal gradient method with respect to a worst-case bound of the composite gradient mapping. The proof is based on the worst-case analysis called Performance Estimation Problem in [11].
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1052-6234
DOI:10.1137/16M108940X