TY - GEN
T1 - Surrogate models for mixed discrete-continuous variables
AU - Swiler, Laura P.
AU - Hough, Patricia D.
AU - Qian, Peter
AU - Xu, Xu
AU - Storlie, Curtis
AU - Lee, Herbert
PY - 2014
Y1 - 2014
N2 - Large-scale computational models have become common tools for analyzing complex man-made systems. However, when coupled with optimization or uncertainty quantification methods in order to conduct extensive model exploration and analysis, the computational expense quickly becomes intractable. Furthermore, these models may have both continuous and discrete parameters. One common approach to mitigating the computational expense is the use of response surface approximations. While well developed for models with continuous parameters, they are still new and largely untested for models with both continuous and discrete parameters. In this work, we describe and investigate the performance of three types of response surfaces developed for mixed-variable models: Adaptive Component Selection and Shrinkage Operator, Treed Gaussian Process, and Gaussian Process with Special Correlation Functions. We focus our efforts on test problems with a small number of parameters of interest, a characteristic of many physics-based engineering models. We present the results of our studies and offer some insights regarding the performance of each response surface approximation method.
AB - Large-scale computational models have become common tools for analyzing complex man-made systems. However, when coupled with optimization or uncertainty quantification methods in order to conduct extensive model exploration and analysis, the computational expense quickly becomes intractable. Furthermore, these models may have both continuous and discrete parameters. One common approach to mitigating the computational expense is the use of response surface approximations. While well developed for models with continuous parameters, they are still new and largely untested for models with both continuous and discrete parameters. In this work, we describe and investigate the performance of three types of response surfaces developed for mixed-variable models: Adaptive Component Selection and Shrinkage Operator, Treed Gaussian Process, and Gaussian Process with Special Correlation Functions. We focus our efforts on test problems with a small number of parameters of interest, a characteristic of many physics-based engineering models. We present the results of our studies and offer some insights regarding the performance of each response surface approximation method.
UR - http://www.scopus.com/inward/record.url?scp=84958532603&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84958532603&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-04280-0_21
DO - 10.1007/978-3-319-04280-0_21
M3 - Conference contribution
AN - SCOPUS:84958532603
SN - 9783319042794
T3 - Studies in Computational Intelligence
SP - 181
EP - 202
BT - Constraint Programming and Decision Making
PB - Springer Verlag
ER -