DocumentCode :
618035
Title :
Surrogate model selection for evolutionary multiobjective optimization
Author :
Pilat, M. ; Neruda, Roman
Author_Institution :
Fac. of Math. & Phys., Charles Univ. in Prague, Prague, Czech Republic
fYear :
2013
fDate :
20-23 June 2013
Firstpage :
1860
Lastpage :
1867
Abstract :
In surrogate evolutionary algorithms, usually the type of surrogate model is chosen beforehand, and it is never changed during the run of the evolution. Moreover, the reasoning why a particular type of model was chosen is often missing. In this paper, we present a framework which in each generation selects the most suitable surrogate from a set of models based on some pre-defined criteria. The results based on different types of model selectors are compared, and the dynamics of the evolution together with the change of the selected model type during the run of the evolutionary algorithm are discussed.
Keywords :
evolutionary computation; optimisation; evolutionary algorithm; evolutionary multiobjective optimization; predefined criteria; surrogate model selection; Computational modeling; Evolutionary computation; Heuristic algorithms; Linear programming; Mean square error methods; Polynomials; Training; Multiobjective optimization; evolutionary algorithm; meta-model; model selection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation (CEC), 2013 IEEE Congress on
Conference_Location :
Cancun
Print_ISBN :
978-1-4799-0453-2
Electronic_ISBN :
978-1-4799-0452-5
Type :
conf
DOI :
10.1109/CEC.2013.6557786
Filename :
6557786
Link To Document :
بازگشت