Quality Gain Analysis of the Weighted Recombination Evolution Strategy on General Convex Quadratic Functions

Youhei Akimoto 1 Anne Auger 2, 3, 4 Nikolaus Hansen 2, 3, 4
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
3 RANDOPT - Randomized Optimisation
Inria Saclay - Ile de France
Abstract : We investigate evolution strategies with weighted recombi-nation on general convex quadratic functions. We derive the asymptotic quality gain in the limit of the dimension to infinity, and derive the optimal recombination weights and the optimal step-size. This work is an extension of previous works where the asymptotic quality gain of evolution strategies with weighted recombination was derived on the infinite dimensional sphere function. Moreover, for a finite dimensional search space, we derive rigorous bounds for the quality gain on a general quadratic function. They reveal the dependency of the quality gain both in the eigenvalue distribution of the Hessian matrix and on the recombina-tion weights. Taking the search space dimension to infinity , it turns out that the optimal recombination weights are independent of the Hessian matrix, i.e., the recombination weights optimal for the sphere function are optimal for convex quadratic functions.
Type de document :
Communication dans un congrès
Proceedings of the 14th ACM/SIGEVO Conference on Foundations of Genetic Algorithms, FOGA, Jan 2017, Copenhagen, Denmark. pp.111-126, 2017, 〈http://foga-2017.sigevo.org/index.html/tiki-index.php?page=HomePage〉. 〈10.1145/3040718.3040720〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01516326
Contributeur : Nikolaus Hansen <>
Soumis le : dimanche 30 avril 2017 - 10:52:29
Dernière modification le : jeudi 5 avril 2018 - 12:30:12
Document(s) archivé(s) le : lundi 31 juillet 2017 - 12:30:06

Fichier

akimoto2017quality.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Youhei Akimoto, Anne Auger, Nikolaus Hansen. Quality Gain Analysis of the Weighted Recombination Evolution Strategy on General Convex Quadratic Functions. Proceedings of the 14th ACM/SIGEVO Conference on Foundations of Genetic Algorithms, FOGA, Jan 2017, Copenhagen, Denmark. pp.111-126, 2017, 〈http://foga-2017.sigevo.org/index.html/tiki-index.php?page=HomePage〉. 〈10.1145/3040718.3040720〉. 〈hal-01516326〉

Partager

Métriques

Consultations de la notice

294

Téléchargements de fichiers

84