skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Exploratory designs for computational experiments

Abstract

Recent work by Johnson, Moore and Ylvisaker (1990) establishes equivalence of the maximin distance design criterion and an entropy criterion motivated by function prediction in a Bayesian setting. The latter criterion has been used by Currin, Mitchell, Morris, and Ylvisaker (1991) to design experiments for which the motivating application is approximation of a complex deterministic computer model. Because computer experiments often have a large number of controlled variables (inputs), maximin designs of moderate size are often concentrated in the corners of the cuboidal design region, i.e. each input is represented at only two levels. Here we will examine some maximin distance designs constructed within the class of Latin hypercube arrangements. The goal of this is to find designs which offer a compromise between the entropy/maximin criterion, and good projective properties in each dimension (as guaranteed by Latin hypercubes). A simulated annealing search algorithm is persented for constructing these designs, and patterns apparent in the optimal designs are discussed.

Authors:
;
Publication Date:
Research Org.:
Oak Ridge National Lab., TN (United States)
Sponsoring Org.:
USDOE, Washington, DC (United States)
OSTI Identifier:
10184343
Report Number(s):
ORNL/TM-12045
ON: DE93002354
DOE Contract Number:  
AC05-84OR21400
Resource Type:
Technical Report
Resource Relation:
Other Information: PBD: Oct 1992
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; ALGORITHMS; DESIGN; COMPUTERIZED SIMULATION; FUNCTIONS; HYPERCUBE COMPUTERS; COMPUTER ARCHITECTURE; 990200; MATHEMATICS AND COMPUTERS

Citation Formats

Morris, M X, and Mitchell, T J. Exploratory designs for computational experiments. United States: N. p., 1992. Web. doi:10.2172/10184343.
Morris, M X, & Mitchell, T J. Exploratory designs for computational experiments. United States. https://doi.org/10.2172/10184343
Morris, M X, and Mitchell, T J. Thu . "Exploratory designs for computational experiments". United States. https://doi.org/10.2172/10184343. https://www.osti.gov/servlets/purl/10184343.
@article{osti_10184343,
title = {Exploratory designs for computational experiments},
author = {Morris, M X and Mitchell, T J},
abstractNote = {Recent work by Johnson, Moore and Ylvisaker (1990) establishes equivalence of the maximin distance design criterion and an entropy criterion motivated by function prediction in a Bayesian setting. The latter criterion has been used by Currin, Mitchell, Morris, and Ylvisaker (1991) to design experiments for which the motivating application is approximation of a complex deterministic computer model. Because computer experiments often have a large number of controlled variables (inputs), maximin designs of moderate size are often concentrated in the corners of the cuboidal design region, i.e. each input is represented at only two levels. Here we will examine some maximin distance designs constructed within the class of Latin hypercube arrangements. The goal of this is to find designs which offer a compromise between the entropy/maximin criterion, and good projective properties in each dimension (as guaranteed by Latin hypercubes). A simulated annealing search algorithm is persented for constructing these designs, and patterns apparent in the optimal designs are discussed.},
doi = {10.2172/10184343},
url = {https://www.osti.gov/biblio/10184343}, journal = {},
number = ,
volume = ,
place = {United States},
year = {1992},
month = {10}
}