An Estimation of Distribution Algorithm With Cheap and Expensive Local Search Methods

In an estimation of distribution algorithm (EDA), global population distribution is modeled by a probabilistic model, from which new trial solutions are sampled, whereas individual location information is not directly and fully exploited. In this paper, we suggest to combine an EDA with cheap and ex...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on evolutionary computation Ročník 19; číslo 6; s. 807 - 822
Hlavní autoři: Zhou, Aimin, Sun, Jianyong, Zhang, Qingfu
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.12.2015
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Computational modeling
Convergence
distribution information
estimation of distribution algorithm
global optimisation
Histograms
location information
Optimization
Search methods
Sociology
univariate marginal distribution algorithm
Distribution information
estimation of distribution algorithm (EDA)
location information
global optimization
univariate marginal distribution algorithm (UMDA)
ISSN:1089-778X, 1941-0026
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In an estimation of distribution algorithm (EDA), global population distribution is modeled by a probabilistic model, from which new trial solutions are sampled, whereas individual location information is not directly and fully exploited. In this paper, we suggest to combine an EDA with cheap and expensive local search (LS) methods for making use of both global statistical information and individual location information. In our approach, part of a new solution is sampled from a modified univariate histogram probabilistic model and the rest is generated by refining a parent solution through a cheap LS method that does not need any function evaluation. When the population has converged, an expensive LS method is applied to improve a promising solution found so far. Controlled experiments have been carried out to investigate the effects of the algorithm components and the control parameters, the scalability on the number of variables, and the running time. The proposed algorithm has been compared with two state-of-the-art algorithms on two test suites of 27 test instances. Experimental results have shown that, for simple test instances, our algorithm can produce better or similar solutions but with faster convergence speed than the compared methods and for some complicated test instances it can find better solutions.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1089-778X
1941-0026
DOI:10.1109/TEVC.2014.2387433