Lower Bounds for Comparison Based Evolution Strategies using VC-dimension and Sign Patterns - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Algorithmica Année : 2010

Lower Bounds for Comparison Based Evolution Strategies using VC-dimension and Sign Patterns

Résumé

We derive lower bounds on the convergence rate of comparison based or selection based algorithms, improving existing results in the continuous setting, and extending them to non-trivial results in the discrete case. This is achieved by considering the VC-dimension of the level sets of the fitness functions; results are then obtained through the use of the shatter function lemma. In the special case of optimization of the sphere function, improved lower bounds are obtained by an argument based on the number of sign patterns.
Fichier principal
Vignette du fichier
evolution.pdf (281.18 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00452791 , version 1 (03-02-2010)

Identifiants

  • HAL Id : inria-00452791 , version 1

Citer

Hervé Fournier, Olivier Teytaud. Lower Bounds for Comparison Based Evolution Strategies using VC-dimension and Sign Patterns. Algorithmica, 2010. ⟨inria-00452791⟩
459 Consultations
394 Téléchargements

Partager

Gmail Facebook X LinkedIn More