Log-linear Convergence of the Scale-invariant $(\mu/\mu_w,\lambda)$-{ES} and Optimal $\mu$ for Intermediate Recombination for Large Population Sizes - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Log-linear Convergence of the Scale-invariant $(\mu/\mu_w,\lambda)$-{ES} and Optimal $\mu$ for Intermediate Recombination for Large Population Sizes

Mohamed Jebalia
  • Fonction : Auteur
  • PersonId : 842777
Anne Auger
  • Fonction : Auteur
  • PersonId : 751513
  • IdHAL : anne-auger

Résumé

Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this paper, we study the convergence of the (mu/mu_w,lambda)-ES, an ES with weighted recombination, and derive its optimal convergence rate and optimal mu especially for large population sizes. First, we theoretically prove the log-linear convergence of the algorithm using a scale-invariant adaptation rule for the step-size and minimizing spherical objective functions and identify its convergence rate as the expectation of an underlying random variable. Then, using Monte-Carlo computations of the convergence rate in the case of equal weights, we derive optimal values for mu that we compare with previously proposed rules. Our numerical computations show also a dependency of the optimal convergence rate in ln(lambda) in agreement with previous theoretical results.
Fichier principal
Vignette du fichier
ppsn2010JebaliaAuger.pdf (148.21 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00494478 , version 1 (24-06-2010)

Identifiants

  • HAL Id : inria-00494478 , version 1

Citer

Mohamed Jebalia, Anne Auger. Log-linear Convergence of the Scale-invariant $(\mu/\mu_w,\lambda)$-{ES} and Optimal $\mu$ for Intermediate Recombination for Large Population Sizes. Parallel Problem Solving From Nature (PPSN2010), Sep 2010, Krakow, Poland. pp.xxxx-xxx. ⟨inria-00494478⟩
266 Consultations
273 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More