Global Convergence of the (1 + 1) Evolution Strategy to a Critical Point
Evolutionary Computation · 01.03.2020 · 28 (1) · 27-53
DOI: 10.1162/evco_a_00248 ↗Kurz gefasst
Fachartikel in der Zeitschrift Evolutionary Computation, online erschienen am 01.03.2020. Verfasst von Tobias Glasmachers. Beteiligte Einrichtung: Institute for Neural Computation, Ruhr-University, Bochum, Germany tobias.glasmachers@ini.rub.de. Hauptthemen laut MEDLINE: Algorithms, Biological Evolution. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
We establish global convergence of the (1 + 1) evolution strategy, that is, convergence to a critical point independent of the initial state. More precisely, we show the existence of a critical limit point, using a suitable extension of the notion of a critical point to measurable functions. At its core, the analysis is based on a novel progress guarantee for elitist, rank-based evolutionary algorithms. By applying it to the (1 + 1) evolution strategy we are able to provide an accurate characterization of whether global convergence is guaranteed with full probability, or whether premature convergence is possible. We illustrate our results on a number of example applications ranging from smooth (non-convex) cases over different types of saddle points and ridge functions to discontinuous and extremely rugged problems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute for Neural Computation, Ruhr-University, Bochum, Germany tobias.glasmachers@ini.rub.de.
Zitieren
APA
Glasmachers, T. (2020). Global Convergence of the (1 + 1) Evolution Strategy to a Critical Point. Evolutionary Computation, 28(1), 27-53. https://doi.org/10.1162/evco_a_00248
Vancouver
Glasmachers T. Global Convergence of the (1 + 1) Evolution Strategy to a Critical Point. Evolutionary Computation. 2020;28(1):27-53. doi:10.1162/evco_a_00248
BibTeX
@article{Glasmachers2020,
author = {Glasmachers, Tobias},
title = {Global Convergence of the (1 + 1) Evolution Strategy to a Critical Point},
journal = {Evolutionary Computation},
year = {2020},
volume = {28},
number = {1},
pages = {27--53},
doi = {10.1162/evco_a_00248}
}
EUVIMED