Gradient based criteria for sequential design

Collin B. Erickson, Bruce E Ankenman, Matthew Plumlee, Susan M. Sanchez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Computer simulation experiments are commonly used as an inexpensive alternative to real-world experiments to form a metamodel that approximates the input-output relationship of the real-world experiment. While a user may want to understand the entire response surface, they may also want to focus on interesting regions of the design space, such as where the gradient is large. In this paper we present an algorithm that adaptively runs a simulation experiment that focuses on finding areas of the response surface with a large gradient while also gathering an understanding of the entire surface. We consider the scenario where small batches of points can be run simultaneously, such as with multi-core processors.

Original languageEnglish (US)
Title of host publicationWSC 2018 - 2018 Winter Simulation Conference
Subtitle of host publicationSimulation for a Noble Cause
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages467-478
Number of pages12
ISBN (Electronic)9781538665725
DOIs
StatePublished - Jan 31 2019
Event2018 Winter Simulation Conference, WSC 2018 - Gothenburg, Sweden
Duration: Dec 9 2018Dec 12 2018

Publication series

NameProceedings - Winter Simulation Conference
Volume2018-December
ISSN (Print)0891-7736

Conference

Conference2018 Winter Simulation Conference, WSC 2018
CountrySweden
CityGothenburg
Period12/9/1812/12/18

Fingerprint

Sequential Design
Response Surface
Simulation Experiment
Entire
Gradient
Computer Experiments
Multi-core Processor
Metamodel
Batch
Experiment
Computer Simulation
Experiments
Scenarios
Output
Alternatives
Computer simulation
Relationships
Design

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Erickson, C. B., Ankenman, B. E., Plumlee, M., & Sanchez, S. M. (2019). Gradient based criteria for sequential design. In WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause (pp. 467-478). [8632546] (Proceedings - Winter Simulation Conference; Vol. 2018-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2018.8632546
Erickson, Collin B. ; Ankenman, Bruce E ; Plumlee, Matthew ; Sanchez, Susan M. / Gradient based criteria for sequential design. WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 467-478 (Proceedings - Winter Simulation Conference).
@inproceedings{53808e8c75de4d5795cb5aceda400228,
title = "Gradient based criteria for sequential design",
abstract = "Computer simulation experiments are commonly used as an inexpensive alternative to real-world experiments to form a metamodel that approximates the input-output relationship of the real-world experiment. While a user may want to understand the entire response surface, they may also want to focus on interesting regions of the design space, such as where the gradient is large. In this paper we present an algorithm that adaptively runs a simulation experiment that focuses on finding areas of the response surface with a large gradient while also gathering an understanding of the entire surface. We consider the scenario where small batches of points can be run simultaneously, such as with multi-core processors.",
author = "Erickson, {Collin B.} and Ankenman, {Bruce E} and Matthew Plumlee and Sanchez, {Susan M.}",
year = "2019",
month = "1",
day = "31",
doi = "10.1109/WSC.2018.8632546",
language = "English (US)",
series = "Proceedings - Winter Simulation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "467--478",
booktitle = "WSC 2018 - 2018 Winter Simulation Conference",
address = "United States",

}

Erickson, CB, Ankenman, BE, Plumlee, M & Sanchez, SM 2019, Gradient based criteria for sequential design. in WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause., 8632546, Proceedings - Winter Simulation Conference, vol. 2018-December, Institute of Electrical and Electronics Engineers Inc., pp. 467-478, 2018 Winter Simulation Conference, WSC 2018, Gothenburg, Sweden, 12/9/18. https://doi.org/10.1109/WSC.2018.8632546

Gradient based criteria for sequential design. / Erickson, Collin B.; Ankenman, Bruce E; Plumlee, Matthew; Sanchez, Susan M.

WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc., 2019. p. 467-478 8632546 (Proceedings - Winter Simulation Conference; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Gradient based criteria for sequential design

AU - Erickson, Collin B.

AU - Ankenman, Bruce E

AU - Plumlee, Matthew

AU - Sanchez, Susan M.

PY - 2019/1/31

Y1 - 2019/1/31

N2 - Computer simulation experiments are commonly used as an inexpensive alternative to real-world experiments to form a metamodel that approximates the input-output relationship of the real-world experiment. While a user may want to understand the entire response surface, they may also want to focus on interesting regions of the design space, such as where the gradient is large. In this paper we present an algorithm that adaptively runs a simulation experiment that focuses on finding areas of the response surface with a large gradient while also gathering an understanding of the entire surface. We consider the scenario where small batches of points can be run simultaneously, such as with multi-core processors.

AB - Computer simulation experiments are commonly used as an inexpensive alternative to real-world experiments to form a metamodel that approximates the input-output relationship of the real-world experiment. While a user may want to understand the entire response surface, they may also want to focus on interesting regions of the design space, such as where the gradient is large. In this paper we present an algorithm that adaptively runs a simulation experiment that focuses on finding areas of the response surface with a large gradient while also gathering an understanding of the entire surface. We consider the scenario where small batches of points can be run simultaneously, such as with multi-core processors.

UR - http://www.scopus.com/inward/record.url?scp=85062615191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062615191&partnerID=8YFLogxK

U2 - 10.1109/WSC.2018.8632546

DO - 10.1109/WSC.2018.8632546

M3 - Conference contribution

T3 - Proceedings - Winter Simulation Conference

SP - 467

EP - 478

BT - WSC 2018 - 2018 Winter Simulation Conference

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Erickson CB, Ankenman BE, Plumlee M, Sanchez SM. Gradient based criteria for sequential design. In WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc. 2019. p. 467-478. 8632546. (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2018.8632546