BOA The Bayesian Optimization Algorithm

Abstract

In this paper an algorithm based on the concepts of genetic algorithms that uses an estimation of a probability distribution of promising solutions in order to generate new candidate solutions is proposed To esti mate the distribution techniques for model ing multivariate data by Bayesian networks are used The proposed algorithm identi es reproduces and mixes building blocks up to a speci ed order It is independent of the ordering of the variables in the strings rep resenting the solutions Moreover prior in formation about the problem can be incor porated into the algorithm However prior information is not essential Preliminary ex periments show that the BOA outperforms the simple genetic algorithm even on decom posable functions with tight building blocks as a problem size grows

050'00'02'04'06'08'10'12'14'16
Citations per Year

676 Citations

Semantic Scholar estimates that this publication has 676 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Pelikan1999BOATB, title={BOA The Bayesian Optimization Algorithm}, author={Martin Pelikan and David E. Goldberg and Erick Cant}, year={1999} }