Noisy Optimization: Convergence with a Fixed Number of Resamplings - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Noisy Optimization: Convergence with a Fixed Number of Resamplings

Résumé

It is known that evolution strategies in continuous domains might not converge in the presence of noise. It is also known that, under mild assumptions, and using an increasing number of resamplings, one can mitigate the effect of additive noise and recover convergence. We show new sufficient conditions for the convergence of an evolutionary algorithm with constant number of resamplings; in particular, we get fast rates (log-linear convergence) provided that the variance decreases around the optimum slightly faster than in the so-called multiplicative noise model.
Fichier principal
Vignette du fichier
cauwet.pdf (202.48 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00976063 , version 1 (09-04-2014)

Identifiants

Citer

Marie-Liesse Cauwet. Noisy Optimization: Convergence with a Fixed Number of Resamplings. EvoStar, Apr 2014, Granada, Spain. ⟨hal-00976063⟩
365 Consultations
189 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More