Resource-Aware Parameterizations of EDA - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Resource-Aware Parameterizations of EDA

Sylvain Gelly
  • Function : Author
  • PersonId : 836546
Olivier Teytaud
Christian Cagne
  • Function : Author
  • PersonId : 836547


This paper presents a framework for the theoretical analysis of Estimation of Distribution Algorithms (EDA). Using this framework, derived from the VC-theory, we propose non-asymptotic bounds which depend on: 1) the population size 2) the selection rate, 3) the families of distributions used for the modelling, 4) the dimension, and 5) the number of iterations. To validate these results, optimization algorithms are applied to a context where bounds on resources are crucial, namely Design of Experiments, that is a black-box optimization with very few fitness-values evaluations.
Fichier principal
Vignette du fichier
Resource-Aware_Parameterizations_EDA-CEC-2006.pdf (118.76 Ko) Télécharger le fichier

Dates and versions

inria-00112803 , version 1 (09-11-2006)


  • HAL Id : inria-00112803 , version 1


Sylvain Gelly, Olivier Teytaud, Christian Cagne. Resource-Aware Parameterizations of EDA. Congress on Evolutionary Computation, Jul 2006, Vancouver, BC, Canada. ⟨inria-00112803⟩
162 View
230 Download


Gmail Facebook Twitter LinkedIn More