On the monotonic performance of stochastic kriging predictors

Bing Wang; Jiaqiao Hu

doi:10.1109/WSC.2015.7408539

On the monotonic performance of stochastic kriging predictors

Bing Wang
, Jiaqiao Hu

Applied Mathematics and Statistics

Stony Brook University

Stony Brook University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Stochastic kriging (SK) has been recognized as a useful and effective technique for approximating the response surface of a simulation model. In this paper, we analyze the performance of SK metamodels in a fully sequential setting when design points are selected one at a time. We consider both cases when the trend term in the model is either known or estimated and show that the prediction performance of the corresponding optimal SK predictor is monotonically improving as the number of design points increases. Numerical examples are also provided to illustrate our findings.

Original language	English
Title of host publication	2015 Winter Simulation Conference, WSC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3825-3833
Number of pages	9
ISBN (Electronic)	9781467397438
DOIs	https://doi.org/10.1109/WSC.2015.7408539
State	Published - Feb 16 2016
Event	Winter Simulation Conference, WSC 2015 - Huntington Beach, United States Duration: Dec 6 2015 → Dec 9 2015

Publication series

Name	Proceedings - Winter Simulation Conference
Volume	2016-February

Conference

Conference	Winter Simulation Conference, WSC 2015
Country/Territory	United States
City	Huntington Beach
Period	12/6/15 → 12/9/15

Access to Document

10.1109/WSC.2015.7408539

Cite this

@inproceedings{708040fdc4b34b2abf6a855bda6a4c37,

title = "On the monotonic performance of stochastic kriging predictors",

abstract = "Stochastic kriging (SK) has been recognized as a useful and effective technique for approximating the response surface of a simulation model. In this paper, we analyze the performance of SK metamodels in a fully sequential setting when design points are selected one at a time. We consider both cases when the trend term in the model is either known or estimated and show that the prediction performance of the corresponding optimal SK predictor is monotonically improving as the number of design points increases. Numerical examples are also provided to illustrate our findings.",

author = "Bing Wang and Jiaqiao Hu",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; Winter Simulation Conference, WSC 2015 ; Conference date: 06-12-2015 Through 09-12-2015",

year = "2016",

month = feb,

day = "16",

doi = "10.1109/WSC.2015.7408539",

language = "English",

series = "Proceedings - Winter Simulation Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3825--3833",

booktitle = "2015 Winter Simulation Conference, WSC 2015",

}

Wang, B & Hu, J 2016, On the monotonic performance of stochastic kriging predictors. in 2015 Winter Simulation Conference, WSC 2015., 7408539, Proceedings - Winter Simulation Conference, vol. 2016-February, Institute of Electrical and Electronics Engineers Inc., pp. 3825-3833, Winter Simulation Conference, WSC 2015, Huntington Beach, United States, 12/6/15. https://doi.org/10.1109/WSC.2015.7408539

On the monotonic performance of stochastic kriging predictors. / Wang, Bing; Hu, Jiaqiao.
2015 Winter Simulation Conference, WSC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 3825-3833 7408539 (Proceedings - Winter Simulation Conference; Vol. 2016-February).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On the monotonic performance of stochastic kriging predictors

AU - Wang, Bing

AU - Hu, Jiaqiao

PY - 2016/2/16

Y1 - 2016/2/16

N2 - Stochastic kriging (SK) has been recognized as a useful and effective technique for approximating the response surface of a simulation model. In this paper, we analyze the performance of SK metamodels in a fully sequential setting when design points are selected one at a time. We consider both cases when the trend term in the model is either known or estimated and show that the prediction performance of the corresponding optimal SK predictor is monotonically improving as the number of design points increases. Numerical examples are also provided to illustrate our findings.

AB - Stochastic kriging (SK) has been recognized as a useful and effective technique for approximating the response surface of a simulation model. In this paper, we analyze the performance of SK metamodels in a fully sequential setting when design points are selected one at a time. We consider both cases when the trend term in the model is either known or estimated and show that the prediction performance of the corresponding optimal SK predictor is monotonically improving as the number of design points increases. Numerical examples are also provided to illustrate our findings.

UR - https://www.scopus.com/pages/publications/84962921449

U2 - 10.1109/WSC.2015.7408539

DO - 10.1109/WSC.2015.7408539

M3 - Conference contribution

T3 - Proceedings - Winter Simulation Conference

SP - 3825

EP - 3833

BT - 2015 Winter Simulation Conference, WSC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - Winter Simulation Conference, WSC 2015

Y2 - 6 December 2015 through 9 December 2015

ER -

On the monotonic performance of stochastic kriging predictors

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this