Title :
Adaptive sampling for optimization under uncertainty
Author :
Wan, Z. ; Igusa, T.
Author_Institution :
Dept. of Civil Eng., Johns Hopkins Univ., Baltimore, MD
Abstract :
The problems of interest are where the objective function must be evaluated using sampling techniques. The sampled function values are used to build an approximation to the response surface over the product space of uncertainties and design variables. This approximation is successively used in the integration over the space of uncertainties and in the optimization (minimization) over the space of design variables. A surrogate-based trust region method is used to determine a succession of design points for optimization
Keywords :
approximation theory; minimisation; sampling methods; uncertainty handling; minimization; optimization; sampling techniques; surrogate-based trust region method; Approximation algorithms; Civil engineering; Convergence; Design optimization; Estimation error; History; Response surface methodology; Sampling methods; Statistics; Uncertainty;
Conference_Titel :
Uncertainty Modeling and Analysis, 2003. ISUMA 2003. Fourth International Symposium on
Conference_Location :
College Park, MD
Print_ISBN :
0-7695-1997-0
DOI :
10.1109/ISUMA.2003.1236195
