Global optimization of deceptive functions with sparse sampling
Global optimization of deceptive functions with sparse sampling
This paper introduces a new method of calculating the expected improvement infill criterion, which does not rely on accurate model parameter estimation. The parameter estimation is embedded within the search of the infill criterion, wherein parameter changes are assessed using likelihood ratio tests. Unlike the traditional expected improvement, a new formulation we present cannot be 'fooled' by unlucky sampling or deceptive functions. The new method is introduced both mathematically and illustratively using a one-variable test function. It is then shown to outperform traditional expected improvement when optimizing the geometry of a passive vibration isolating truss.
Forrester, Alexander I.J.
176bf191-3fc2-46b4-80e0-9d9a0cd7a572
Jones, Donald R.
7afc990f-d8c7-4053-8f32-175611c9aaff
September 2008
Forrester, Alexander I.J.
176bf191-3fc2-46b4-80e0-9d9a0cd7a572
Jones, Donald R.
7afc990f-d8c7-4053-8f32-175611c9aaff
Forrester, Alexander I.J. and Jones, Donald R.
(2008)
Global optimization of deceptive functions with sparse sampling.
12th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Victoria, Canada.
10 - 12 Sep 2008.
15 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper introduces a new method of calculating the expected improvement infill criterion, which does not rely on accurate model parameter estimation. The parameter estimation is embedded within the search of the infill criterion, wherein parameter changes are assessed using likelihood ratio tests. Unlike the traditional expected improvement, a new formulation we present cannot be 'fooled' by unlucky sampling or deceptive functions. The new method is introduced both mathematically and illustratively using a one-variable test function. It is then shown to outperform traditional expected improvement when optimizing the geometry of a passive vibration isolating truss.
Text
ForresterandJones.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Published date: September 2008
Venue - Dates:
12th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Victoria, Canada, 2008-09-10 - 2008-09-12
Identifiers
Local EPrints ID: 63927
URI: http://eprints.soton.ac.uk/id/eprint/63927
PURE UUID: 9c9c43c0-31a0-4e82-9792-b6aa926a9699
Catalogue record
Date deposited: 19 Nov 2008
Last modified: 15 Mar 2024 11:44
Export record
Contributors
Author:
Donald R. Jones
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics