The correlation-triggered adaptive variance scaling IDEA
- 8 July 2006
- proceedings article
- Published by Association for Computing Machinery (ACM)
- p. 397-404
- https://doi.org/10.1145/1143997.1144071
Abstract
It has previously been shown analytically and experimentally that continuous Estimation of Distribution Algorithms (EDAs) based on the normal pdf can easily suffer from premature convergence. This paper takes a principled first step towards solving this problem. First, prerequisites for the successful use of search distributions in EDAs are presented. Then, an adaptive variance scaling theme is introduced that aims at reducing the risk of premature convergence. Integrating the scheme into the iterated density--estimation evolutionary algorithm (IDEA) yields the correlation-triggered adaptive variance scaling IDEA (CT-AVS-IDEA). The CT-AVS-IDEA is compared to the original IDEA and the Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) on a wide range of unimodal test-problems by means of a scalability analysis. It is found that the average number of fitness evaluations grows subquadratically with the dimensionality, competitively with the CMA-ES. In addition, CT-AVS-IDEA is indeed found to enlarge the class of problems that continuous EDAs can solve reliably.Keywords
This publication has 12 references indexed in Scilit:
- On the importance of diversity maintenance in estimation of distribution algorithmsPublished by Association for Computing Machinery (ACM) ,2005
- Learning probability distributions in continuous evolutionary algorithms – a comparative reviewNatural Computing, 2004
- Real-Coded Bayesian Optimization Algorithm: Bringing the Strength of BOA into the Continuous WorldPublished by Springer Nature ,2004
- A Mixed Bayesian Optimization Algorithm with Variance AdaptationPublished by Springer Nature ,2004
- Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES)Evolutionary Computation, 2003
- Mathematical modelling of UMDAc algorithm with tournament selection. Behaviour on linear and quadratic functionsInternational Journal of Approximate Reasoning, 2002
- Completely Derandomized Self-Adaptation in Evolution StrategiesEvolutionary Computation, 2001
- FDA -A Scalable Evolutionary Algorithm for the Optimization of Additively Decomposed FunctionsEvolutionary Computation, 1999
- A Comparison of Selection Schemes Used in Evolutionary AlgorithmsEvolutionary Computation, 1996
- From recombination of genes to the estimation of distributions I. Binary parametersPublished by Springer Nature ,1996