Stopping rules for steepest ascent in experimental optimization

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Steepest ascent is used for experimental optimization in the area of Response Surface Methodology (RSM). The usual recommendation in RSM is to stop experimenting along the direction of the gradient of the response when no further improvement is observed. This statement has resulted in different empirical stopping rules followed in practice, from stopping at the first point where there is an observed drop in response, to the cautious "3-in-a-row" rule in which the search is stopped only after 3 consecutive response drops. A formal sequential stopping rule has been proposed by Myers and Khuri. This paper investigates the performance of the M&K stopping rule compared to the empirical rules used in practice. A new recursive procedure that iteratively estimates a parabola along the search direction is introduced and compared with the other rules. It is shown, based on simulated line searches, that both the proposed recursive procedure and the M&K procedure perform considerably better than the empirical rules. Instances in which each of these two methods should be used are discussed. Among the empirical rules, only the 3-in-a-row rule provides reliable estimates of the location of maximum response, but this is achieved at the expense of a considerable larger number of experiments than other rules. The 2-in-a-row and first drop rules performed much worse, failing to detect the location of the maximum mean response even under favorable conditions (i.e., under low noise and large curvature levels in the response).

Original languageEnglish (US)
Pages (from-to)1599-1615
Number of pages17
JournalCommunications in Statistics Part B: Simulation and Computation
Volume26
Issue number4
StatePublished - Dec 1 1997

Fingerprint

Stopping Rule
Ascent
Optimization
Response Surface Methodology
Experiments
Parabola
Line Search
Estimate
Consecutive
Recommendations
Curvature
Gradient

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modeling and Simulation

Cite this

@article{a484c4e8d9ed4c1c9df8a674f9e33bf8,
title = "Stopping rules for steepest ascent in experimental optimization",
abstract = "Steepest ascent is used for experimental optimization in the area of Response Surface Methodology (RSM). The usual recommendation in RSM is to stop experimenting along the direction of the gradient of the response when no further improvement is observed. This statement has resulted in different empirical stopping rules followed in practice, from stopping at the first point where there is an observed drop in response, to the cautious {"}3-in-a-row{"} rule in which the search is stopped only after 3 consecutive response drops. A formal sequential stopping rule has been proposed by Myers and Khuri. This paper investigates the performance of the M&K stopping rule compared to the empirical rules used in practice. A new recursive procedure that iteratively estimates a parabola along the search direction is introduced and compared with the other rules. It is shown, based on simulated line searches, that both the proposed recursive procedure and the M&K procedure perform considerably better than the empirical rules. Instances in which each of these two methods should be used are discussed. Among the empirical rules, only the 3-in-a-row rule provides reliable estimates of the location of maximum response, but this is achieved at the expense of a considerable larger number of experiments than other rules. The 2-in-a-row and first drop rules performed much worse, failing to detect the location of the maximum mean response even under favorable conditions (i.e., under low noise and large curvature levels in the response).",
author = "{Del Castillo}, Enrique",
year = "1997",
month = "12",
day = "1",
language = "English (US)",
volume = "26",
pages = "1599--1615",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

Stopping rules for steepest ascent in experimental optimization. / Del Castillo, Enrique.

In: Communications in Statistics Part B: Simulation and Computation, Vol. 26, No. 4, 01.12.1997, p. 1599-1615.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Stopping rules for steepest ascent in experimental optimization

AU - Del Castillo, Enrique

PY - 1997/12/1

Y1 - 1997/12/1

N2 - Steepest ascent is used for experimental optimization in the area of Response Surface Methodology (RSM). The usual recommendation in RSM is to stop experimenting along the direction of the gradient of the response when no further improvement is observed. This statement has resulted in different empirical stopping rules followed in practice, from stopping at the first point where there is an observed drop in response, to the cautious "3-in-a-row" rule in which the search is stopped only after 3 consecutive response drops. A formal sequential stopping rule has been proposed by Myers and Khuri. This paper investigates the performance of the M&K stopping rule compared to the empirical rules used in practice. A new recursive procedure that iteratively estimates a parabola along the search direction is introduced and compared with the other rules. It is shown, based on simulated line searches, that both the proposed recursive procedure and the M&K procedure perform considerably better than the empirical rules. Instances in which each of these two methods should be used are discussed. Among the empirical rules, only the 3-in-a-row rule provides reliable estimates of the location of maximum response, but this is achieved at the expense of a considerable larger number of experiments than other rules. The 2-in-a-row and first drop rules performed much worse, failing to detect the location of the maximum mean response even under favorable conditions (i.e., under low noise and large curvature levels in the response).

AB - Steepest ascent is used for experimental optimization in the area of Response Surface Methodology (RSM). The usual recommendation in RSM is to stop experimenting along the direction of the gradient of the response when no further improvement is observed. This statement has resulted in different empirical stopping rules followed in practice, from stopping at the first point where there is an observed drop in response, to the cautious "3-in-a-row" rule in which the search is stopped only after 3 consecutive response drops. A formal sequential stopping rule has been proposed by Myers and Khuri. This paper investigates the performance of the M&K stopping rule compared to the empirical rules used in practice. A new recursive procedure that iteratively estimates a parabola along the search direction is introduced and compared with the other rules. It is shown, based on simulated line searches, that both the proposed recursive procedure and the M&K procedure perform considerably better than the empirical rules. Instances in which each of these two methods should be used are discussed. Among the empirical rules, only the 3-in-a-row rule provides reliable estimates of the location of maximum response, but this is achieved at the expense of a considerable larger number of experiments than other rules. The 2-in-a-row and first drop rules performed much worse, failing to detect the location of the maximum mean response even under favorable conditions (i.e., under low noise and large curvature levels in the response).

UR - http://www.scopus.com/inward/record.url?scp=0031269330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031269330&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031269330

VL - 26

SP - 1599

EP - 1615

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 4

ER -