Boosted surrogate models in evolutionary optimization?

Information Technologies - Applications and Theory 2009.

计算机科学;

Martin Hole·na

Others  :  http://ceur-ws.org/Vol-584/paper3.pdf
PID  :  42714

学科分类：计算机科学（综合）

来源: CEUR

【 摘 要 】

The paper deals with surrogate modelling,a modern approach to the optimization of empirical ob- jective functions. The approach leads to a substantial de- crease of time and costs of evaluation of the objective func- tion, a property that is particularly attractive in evolution- ary optimization. In the paper, an extension of surrogate modelling with regression boosting is proposed. Such an ex- tension increases the accuracy of surrogate models, thus also the agreement between results of surrogate modelling and results of the intended optimization of the original ob- jective function. The proposed extension is illustrated on a case study in the area of searching catalytic materials op- timal with respect to their behaviour in a particular chem- ical reaction. A genetic algorithm developed speci¯cally for this application area is employed for optimization, multi- layer perceptrons serve as surrogate models, and a method called AdaBoost.R2 is used for boosting. Results of the case study clearly con¯rm the usefulness of boosting for surro-