A Generalized Markov-Chain Modelling Approach to (1,λ)-ES Linear Optimization

Alexandre Chotard 1, 2 Martin Holeňa 3
1 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : Several recent publications investigated Markov-chain mod-elling of linear optimization by a (1, λ)-ES, considering both uncon-strained and linearly constrained optimization, and both constant and varying step size. All of them assume normality of the involved random steps, and while this is consistent with a black-box scenario, information on the function to be optimized (e.g. separability) may be exploited by the use of another distribution. The objective of our contribution is to complement previous studies realized with normal steps, and to give suf-ficient conditions on the distribution of the random steps for the success of a constant step-size (1, λ)-ES on the simple problem of a linear func-tion with a linear constraint. The decomposition of a multidimensional distribution into its marginals and the copula combining them is applied to the new distributional assumptions, particular attention being paid to distributions with Archimedean copulas.
Type de document :
Communication dans un congrès
Parallel Problem Solving from Nature – PPSN XIII, Sep 2014, Ljubljana, Slovenia. Springer, Lecture Notes in Computer Science, 8672, pp.902 - 911, 2014, Lecture Notes in Computer Science. 〈http://ppsn2014.ijs.si/〉. 〈10.1007/978-3-319-10762-2_89〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01091494
Contributeur : Alexandre Chotard <>
Soumis le : vendredi 5 décembre 2014 - 15:03:33
Dernière modification le : jeudi 5 avril 2018 - 12:30:12
Document(s) archivé(s) le : lundi 9 mars 2015 - 06:03:41

Fichiers

ppsn2014linearconstraintgenera...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Alexandre Chotard, Martin Holeňa. A Generalized Markov-Chain Modelling Approach to (1,λ)-ES Linear Optimization. Parallel Problem Solving from Nature – PPSN XIII, Sep 2014, Ljubljana, Slovenia. Springer, Lecture Notes in Computer Science, 8672, pp.902 - 911, 2014, Lecture Notes in Computer Science. 〈http://ppsn2014.ijs.si/〉. 〈10.1007/978-3-319-10762-2_89〉. 〈hal-01091494〉

Partager

Métriques

Consultations de la notice

342

Téléchargements de fichiers

110