Skip to Main content Skip to Navigation
Conference papers

Resource-Aware Parameterizations of EDA

Sylvain Gelly 1 Olivier Teytaud 1 Christian Cagne 1
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : 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.
Complete list of metadata

Cited literature [43 references]  Display  Hide  Download

https://hal.inria.fr/inria-00112803
Contributor : Sylvain Gelly <>
Submitted on : Thursday, November 9, 2006 - 4:56:23 PM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM
Long-term archiving on: : Thursday, September 20, 2012 - 2:35:29 PM

Identifiers

  • HAL Id : inria-00112803, version 1

Collections

Citation

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

Share

Metrics

Record views

399

Files downloads

367