Statistical testing of optimality conditions in multiresponse simulation-based optimization

Bert Bettonvil, Enrique Del Castillo, Jack P C Kleijnen

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

This article studies simulation-based optimization with multiple outputs. It assumes that the simulation model has one random objective function and must satisfy given constraints on the other random outputs. It presents a statistical procedure for testing whether a specific input combination (proposed by some optimization heuristic) satisfies the Karush-Kuhn-Tucker (KKT) first-order optimality conditions. The article focuses on "expensive" simulations, which have small sample sizes. The article applies the classic t test to check whether the specific input combination is feasible, and whether any constraints are binding; next, it applies bootstrapping (resampling) to test the estimated gradients in the KKT conditions. The new methodology is applied to three examples, which gives encouraging empirical results.

Original languageEnglish (US)
Pages (from-to)448-458
Number of pages11
JournalEuropean Journal of Operational Research
Volume199
Issue number2
DOIs
StatePublished - Dec 1 2009

Fingerprint

Simulation-based Optimization
Optimality Conditions
Karush-Kuhn-Tucker Conditions
First-order Optimality Conditions
Heuristic Optimization
Testing
t-test
Output
Random Function
Bootstrapping
Small Sample Size
Resampling
Simulation Model
Objective function
Gradient
Methodology
Simulation
Optimality conditions
Statistical testing
Small sample

All Science Journal Classification (ASJC) codes

  • Management Science and Operations Research
  • Modeling and Simulation
  • Information Systems and Management

Cite this

@article{2d699cfffb304ae48d99f0b1d7f3c2ff,
title = "Statistical testing of optimality conditions in multiresponse simulation-based optimization",
abstract = "This article studies simulation-based optimization with multiple outputs. It assumes that the simulation model has one random objective function and must satisfy given constraints on the other random outputs. It presents a statistical procedure for testing whether a specific input combination (proposed by some optimization heuristic) satisfies the Karush-Kuhn-Tucker (KKT) first-order optimality conditions. The article focuses on {"}expensive{"} simulations, which have small sample sizes. The article applies the classic t test to check whether the specific input combination is feasible, and whether any constraints are binding; next, it applies bootstrapping (resampling) to test the estimated gradients in the KKT conditions. The new methodology is applied to three examples, which gives encouraging empirical results.",
author = "Bert Bettonvil and {Del Castillo}, Enrique and Kleijnen, {Jack P C}",
year = "2009",
month = "12",
day = "1",
doi = "10.1016/j.ejor.2008.11.050",
language = "English (US)",
volume = "199",
pages = "448--458",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier",
number = "2",

}

Statistical testing of optimality conditions in multiresponse simulation-based optimization. / Bettonvil, Bert; Del Castillo, Enrique; Kleijnen, Jack P C.

In: European Journal of Operational Research, Vol. 199, No. 2, 01.12.2009, p. 448-458.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Statistical testing of optimality conditions in multiresponse simulation-based optimization

AU - Bettonvil, Bert

AU - Del Castillo, Enrique

AU - Kleijnen, Jack P C

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This article studies simulation-based optimization with multiple outputs. It assumes that the simulation model has one random objective function and must satisfy given constraints on the other random outputs. It presents a statistical procedure for testing whether a specific input combination (proposed by some optimization heuristic) satisfies the Karush-Kuhn-Tucker (KKT) first-order optimality conditions. The article focuses on "expensive" simulations, which have small sample sizes. The article applies the classic t test to check whether the specific input combination is feasible, and whether any constraints are binding; next, it applies bootstrapping (resampling) to test the estimated gradients in the KKT conditions. The new methodology is applied to three examples, which gives encouraging empirical results.

AB - This article studies simulation-based optimization with multiple outputs. It assumes that the simulation model has one random objective function and must satisfy given constraints on the other random outputs. It presents a statistical procedure for testing whether a specific input combination (proposed by some optimization heuristic) satisfies the Karush-Kuhn-Tucker (KKT) first-order optimality conditions. The article focuses on "expensive" simulations, which have small sample sizes. The article applies the classic t test to check whether the specific input combination is feasible, and whether any constraints are binding; next, it applies bootstrapping (resampling) to test the estimated gradients in the KKT conditions. The new methodology is applied to three examples, which gives encouraging empirical results.

UR - http://www.scopus.com/inward/record.url?scp=67349243376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349243376&partnerID=8YFLogxK

U2 - 10.1016/j.ejor.2008.11.050

DO - 10.1016/j.ejor.2008.11.050

M3 - Article

AN - SCOPUS:67349243376

VL - 199

SP - 448

EP - 458

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 2

ER -