On the codimension of the set of optima: large scale optimisation with few relevant variables - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

On the codimension of the set of optima: large scale optimisation with few relevant variables

Résumé

The complexity of continuous optimisation by comparison-based algorithms has been developed in several recent papers.Roughly speaking, these papers conclude that a precision can be reached with cost Θ(n log(1//)) in dimension n within polylogarithmic factors for the sphere function. Compared to other (non comparison-based) algorithms, this rate is not excellent; on the other hand, it is classically considered that comparison-based algorithms have some robustness advantages, as well as scalability on parallel machines and simplicity. In the present paper we show another advantage, namely resilience to useless variables, thanks to a complexity bound Θ(m log(1//)) where m is the codimension of the set of optima, possibly m << n. In addition, experiments show that some evolutionary algorithms have a negligible computational complexity even in high dimension, making them practical for huge problems with many useless variables.
Fichier principal
Vignette du fichier
EAsource.pdf (1.89 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01194519 , version 1 (07-09-2015)

Identifiants

  • HAL Id : hal-01194519 , version 1

Citer

Vincent Berthier, Olivier Teytaud. On the codimension of the set of optima: large scale optimisation with few relevant variables. Artificial Evolution 2015, 2015, Lyon, France. To appear. ⟨hal-01194519⟩
212 Consultations
213 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More