A generalized worst-case complexity analysis for non-monotone line searches

A generalized worst-case complexity analysis for non-monotone line searches

We study the worst-case complexity of a non-monotone line search framework that covers a wide variety of known techniques published in the literature. In this framework, the non-monotonicity is controlled by a sequence of nonnegative parameters. We obtain complexity bounds to achieve approximate fir...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Numerical algorithms 2021-06, Vol.87 (2), p.779-796
Hauptverfasser: Grapiglia, Geovani N., Sachs, Ekkehard W.
Format: Artikel
Sprache:eng
Schlagworte:
Algebra
Algorithms
Complexity
Computer Science
Estimates
Numeric Computing
Numerical Analysis
Original Paper
Theory of Computation
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We study the worst-case complexity of a non-monotone line search framework that covers a wide variety of known techniques published in the literature. In this framework, the non-monotonicity is controlled by a sequence of nonnegative parameters. We obtain complexity bounds to achieve approximate first-order optimality even when this sequence is not summable.
ISSN:1017-1398
1572-9265
DOI:10.1007/s11075-020-00987-6