Asynchronous Master/Slave MOEAs and Heterogeneous Evaluation Costs

Mouadh Yagoubi 1, 2 Marc Schoenauer 1, 3
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : Parallel master-slave evolutionary algorithms easily lead to linear speed-ups in the case of a small number of nodes \ldots and homogeneous computational costs of the evaluations. However, modern computer now routinely have several hundreds of nodes -- and in many real-world applications in which fitness computation involves heavy numerical simulations, the computational costs of these simulations can greatly vary from one individual to the next. A simple answer to the latter problem is to use asynchronous steady-state reproduction schemes. But the resulting algorithms then differ from the original sequential version, with two consequences: First, the linear speed-up does not hold any more; Second, the convergence might be hindered by the heterogeneity of the evaluation costs. The multi-objective optimization of a diesel engine is first presented, a real-world case study where evaluations require several hours of CPU, and are very heterogeneous in terms of CPU cost. Both the speed-up of asynchronous parallel master/slave algorithms in case of large number of nodes, and their convergence toward the Pareto Front in case of heterogeneous computation times, are then experimentally analyzed on artificial test functions. An alternative selection scheme involving the computational cost of the fitness evaluation is then proposed, that counteracts the effects of heterogeneity on convergence toward the Pareto Front.
Type de document :
Communication dans un congrès
Terence Soule; Jason H. Moore. Genetic and Evolutionary Computation Conference (GECCO 2012), Jul 2012, Philadelphia, United States. ACM Press, pp.1007-1014, 2012
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00689965
Contributeur : Mouadh Yagoubi <>
Soumis le : vendredi 20 avril 2012 - 16:07:57
Dernière modification le : jeudi 5 avril 2018 - 12:30:12
Document(s) archivé(s) le : lundi 26 novembre 2012 - 15:20:25

Fichier

main.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00689965, version 1

Collections

Citation

Mouadh Yagoubi, Marc Schoenauer. Asynchronous Master/Slave MOEAs and Heterogeneous Evaluation Costs. Terence Soule; Jason H. Moore. Genetic and Evolutionary Computation Conference (GECCO 2012), Jul 2012, Philadelphia, United States. ACM Press, pp.1007-1014, 2012. 〈hal-00689965〉

Partager

Métriques

Consultations de la notice

721

Téléchargements de fichiers

1842