Evolutionary Gradient Search Revisited

Evolutionary gradient search (EGS) is an approach to optimization that combines features of gradient strategies with ideas from evolutionary computation. Recently, several modifications to the algorithm have been proposed with the goal of improving its robustness in the presence of noise and its sui...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on evolutionary computation 2007-08, Vol.11 (4), p.480-495
Hauptverfasser: Arnold, D.V., Salomon, R.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Evolutionary gradient search (EGS) is an approach to optimization that combines features of gradient strategies with ideas from evolutionary computation. Recently, several modifications to the algorithm have been proposed with the goal of improving its robustness in the presence of noise and its suitability for implementation on parallel computers. In this paper, the value of the proposed modifications is studied analytically. A scaling law is derived that describes the performance of the algorithm on the noisy sphere model and allows comparing it with competing strategies. The comparisons yield insights into the interplay of mutation, multire combination, and selection. Then, the covariance matrix adaptation mechanism originally formulated for evolution strategies is adapted for use with EGS in order to make the algorithm competitive on objective functions with large condition numbers of their Hessians. The resulting strategy is evaluated experimentally on a number of convex quadratic test functions.
ISSN:1089-778X
1941-0026
DOI:10.1109/TEVC.2006.882427