Communication Dans Un Congrès Année : 2013

Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions

Résumé

We study the linear convergence of a simple evolutionary algorithm on non quasi-convex functions on continuous domains. Assumptions include an assumption on the sampling performed by the evolutionary algorithm (supposed to cover efficiently the neighborhood of the current search point), the conditioning of the objective function (so that the probability of improvement is not too low at each time step, given a correct step size), and the unicity of the optimum.

Fichier principal
Vignette du fichier
linearConvergence.pdf (520.25 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-00907671 , version 1 (21-11-2013)

Licence

Identifiants

  • HAL Id : hal-00907671 , version 1

Citer

Jérémie Decock, Olivier Teytaud. Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions. EA - 11th Biennal International Conference on Artificial Evolution - 2013, Oct 2013, Bordeaux, France. ⟨hal-00907671⟩
312 Consultations
392 Téléchargements

Partager

  • More