PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Resource-Aware Parameterizations of EDA
Sylvain Gelly, Olivier Teytaud and Christian Gagne
In: IEEE CEC 2006 Congress on Evolutionary Computation, 16-21 July 2006, Vancouver, BC, Canada.

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:2433
Deposited By:Sylvain Gelly
Deposited On:22 November 2006