2016
DOI: 10.1155/2016/6723410
|View full text |Cite
|
Sign up to set email alerts
|

An Improved Approach for Estimating the Hyperparameters of the Kriging Model for High-Dimensional Problems through the Partial Least Squares Method

Abstract: During the last years, kriging has become one of the most popular methods in computer simulation and machine learning. Kriging models have been successfully used in many engineering applications, to approximate expensive simulation models. When many input variables are used, kriging is inefficient mainly due to an exorbitant computational time required during its construction. To handle high-dimensional problems (100+), one method is recently proposed that combines kriging with the Partial Least Squares techni… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
37
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
5
3
1

Relationship

2
7

Authors

Journals

citations
Cited by 51 publications
(37 citation statements)
references
References 20 publications
0
37
0
Order By: Relevance
“…In this paper, two new methods for solving high-dimensional constrained optimization problems are developed, both based on SEGO approach: (i) SEGOKPLS uses SEGO with the KPLS model (Bouhlel et al 2016b); and (ii) SEGOKPLS+K uses SEGO with the KPLS+K model (Bouhlel et al 2016a). The SEGOKPLS(+K) algorithms build KPLS(+K) for each output function at each iteration of optimization.…”
Section: Introductionmentioning
confidence: 99%
“…In this paper, two new methods for solving high-dimensional constrained optimization problems are developed, both based on SEGO approach: (i) SEGOKPLS uses SEGO with the KPLS model (Bouhlel et al 2016b); and (ii) SEGOKPLS+K uses SEGO with the KPLS+K model (Bouhlel et al 2016a). The SEGOKPLS(+K) algorithms build KPLS(+K) for each output function at each iteration of optimization.…”
Section: Introductionmentioning
confidence: 99%
“…Beyond 10000 points, computer memory would be an additional limitation. Recent works on Gaussian Processes have introduced strategies to deal with large number of points [137,138] and high-dimensional problems [139,140]. However these approaches remain currently limited to response-only data.…”
Section: Discussionmentioning
confidence: 99%
“…• ONERA's tool, MOE, a Mixture of Experts technique which combines local surrogate models [31]. The local expert could be a polynomial model (linear, quadratic, cubic), a radial basis function or some specific kriging models adapted to high-dimensional problems [32,33]…”
Section: Available Methodsmentioning
confidence: 99%