Convergence analysis of UMDAc with finite populations: A case study on flat landscapes

Yuan, Bo and Gallagher, Marcus (2009). Convergence analysis of UMDAc with finite populations: A case study on flat landscapes. In: Franz Rothlauf and Günther Raidl, Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009. 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009, Montréal, QC, Canada, (477-482). 8-12 July 2009. doi:10.1145/1569901.1569967

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Yuan, Bo
Gallagher, Marcus
Title of paper Convergence analysis of UMDAc with finite populations: A case study on flat landscapes
Formatted title
Convergence analysis of UMDAC with finite populations: A case study on flat landscapes
Conference name 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Conference location Montréal, QC, Canada
Conference dates 8-12 July 2009
Convener The Association for Computing Machinery Special Interest Group on Genetic and Evolutionary Computation (SIGEVO)
Proceedings title Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Journal name Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Place of Publication New York, NY, U.S.A.
Publisher ACM (Association for Computing Machinery) Press
Publication Year 2009
Sub-type Fully published paper
DOI 10.1145/1569901.1569967
Open Access Status
ISBN 9781605583259
1605583251
Editor Franz Rothlauf
Günther Raidl
Volume 910092
Start page 477
End page 482
Total pages 6
Language eng
Formatted Abstract/Summary
This paper presents some new analytical results on the continuous Univariate Marginal Distribution Algorithm (UMDAC), which is a well known Estimation of Distribution Algorithm based on Gaussian distributions. As the extension of the current theoretical work built on the assumption of infinite populations, the convergence behavior of UMDAC with finite populations is formally analyzed. We show both analytically and experimentally that, on flat landscapes, the Gaussian model in UMDAC tends to collapse with high probability, which is an important fact that is not well understood before.
Copyright 2009 ACM
Subjects 0802 Computation Theory and Mathematics
Keyword EDAs
UMDAC
UMDAc
Theory
Finite population
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 4 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 12 Oct 2010, 15:48:19 EST by Jon Swabey on behalf of Faculty Of Engineering, Architecture & Info Tech