On the Optimal Convergence Probability of Univariate Estimation of Distribution Algorithms
Neural and Evolutionary Computing
2010-09-14 v4 Artificial Intelligence
Abstract
In this paper, we obtain bounds on the probability of convergence to the optimal solution for the compact Genetic Algorithm (cGA) and the Population Based Incremental Learning (PBIL). We also give a sufficient condition for convergence of these algorithms to the optimal solution and compute a range of possible values of the parameters of these algorithms for which they converge to the optimal solution with a confidence level.
Cite
@article{arxiv.0901.0597,
title = {On the Optimal Convergence Probability of Univariate Estimation of Distribution Algorithms},
author = {Reza Rastegar},
journal= {arXiv preprint arXiv:0901.0597},
year = {2010}
}
Comments
evolutionary computation