Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization

Russell R. Barton, John S. Ivey

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

18 Citations (Scopus)

Abstract

It is pointed out that the Nelder-Mead simplex method rescaling and shrinking steps make it sensitive to random variations in the response function values, and introduce risks of false convergence on stochastic functions. The authors give analytical and empirical evidence that characterizes false convergence on stochastic functions, and discuss several modifications to reduce the likelihood of false convergence. They describe a computational comparison of several modifications when used to optimize simple stochastic functions of two and ten variables.

Original languageEnglish (US)
Title of host publicationWinter Simulation Conference Proceedings
PublisherPubl by IEEE
Pages945-953
Number of pages9
ISBN (Print)078030181X
StatePublished - Dec 1 1991
Event1991 Winter Simulation Conference Proceedings - Phoenix, AZ, USA
Duration: Dec 8 1991Dec 11 1991

Publication series

NameWinter Simulation Conference Proceedings
ISSN (Print)0275-0708

Other

Other1991 Winter Simulation Conference Proceedings
CityPhoenix, AZ, USA
Period12/8/9112/11/91

Fingerprint

Simplex Method
Stochastic Simulation
Optimization
Rescaling
Response Function
Shrinking
Likelihood
Optimise
False

All Science Journal Classification (ASJC) codes

  • Software
  • Modeling and Simulation
  • Safety, Risk, Reliability and Quality
  • Chemical Health and Safety
  • Applied Mathematics

Cite this

Barton, R. R., & Ivey, J. S. (1991). Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization. In Winter Simulation Conference Proceedings (pp. 945-953). (Winter Simulation Conference Proceedings). Publ by IEEE.
Barton, Russell R. ; Ivey, John S. / Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization. Winter Simulation Conference Proceedings. Publ by IEEE, 1991. pp. 945-953 (Winter Simulation Conference Proceedings).
@inproceedings{b50304fe9443426f86ca8287d13a12a6,
title = "Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization",
abstract = "It is pointed out that the Nelder-Mead simplex method rescaling and shrinking steps make it sensitive to random variations in the response function values, and introduce risks of false convergence on stochastic functions. The authors give analytical and empirical evidence that characterizes false convergence on stochastic functions, and discuss several modifications to reduce the likelihood of false convergence. They describe a computational comparison of several modifications when used to optimize simple stochastic functions of two and ten variables.",
author = "Barton, {Russell R.} and Ivey, {John S.}",
year = "1991",
month = "12",
day = "1",
language = "English (US)",
isbn = "078030181X",
series = "Winter Simulation Conference Proceedings",
publisher = "Publ by IEEE",
pages = "945--953",
booktitle = "Winter Simulation Conference Proceedings",

}

Barton, RR & Ivey, JS 1991, Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization. in Winter Simulation Conference Proceedings. Winter Simulation Conference Proceedings, Publ by IEEE, pp. 945-953, 1991 Winter Simulation Conference Proceedings, Phoenix, AZ, USA, 12/8/91.

Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization. / Barton, Russell R.; Ivey, John S.

Winter Simulation Conference Proceedings. Publ by IEEE, 1991. p. 945-953 (Winter Simulation Conference Proceedings).

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

TY - GEN

T1 - Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization

AU - Barton, Russell R.

AU - Ivey, John S.

PY - 1991/12/1

Y1 - 1991/12/1

N2 - It is pointed out that the Nelder-Mead simplex method rescaling and shrinking steps make it sensitive to random variations in the response function values, and introduce risks of false convergence on stochastic functions. The authors give analytical and empirical evidence that characterizes false convergence on stochastic functions, and discuss several modifications to reduce the likelihood of false convergence. They describe a computational comparison of several modifications when used to optimize simple stochastic functions of two and ten variables.

AB - It is pointed out that the Nelder-Mead simplex method rescaling and shrinking steps make it sensitive to random variations in the response function values, and introduce risks of false convergence on stochastic functions. The authors give analytical and empirical evidence that characterizes false convergence on stochastic functions, and discuss several modifications to reduce the likelihood of false convergence. They describe a computational comparison of several modifications when used to optimize simple stochastic functions of two and ten variables.

UR - http://www.scopus.com/inward/record.url?scp=0026365476&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026365476&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026365476

SN - 078030181X

T3 - Winter Simulation Conference Proceedings

SP - 945

EP - 953

BT - Winter Simulation Conference Proceedings

PB - Publ by IEEE

ER -

Barton RR, Ivey JS. Modifications of the Nedler-Mead simplex method for stochastic simulation response optimization. In Winter Simulation Conference Proceedings. Publ by IEEE. 1991. p. 945-953. (Winter Simulation Conference Proceedings).