A benchmark of kriging-based infill criteria for noisy optimization

Picheny, Victor; Wagner, Tobias; Ginsbourger, David (2013). A benchmark of kriging-based infill criteria for noisy optimization. Structural and Multidisciplinary Optimization, 48(3), pp. 607-626. Springer 10.1007/s00158-013-0919-4

[img]
Preview
Text
__ubnetapp02_user$_brinksma_Downloads_benchmark kriging.pdf - Published Version
Available under License Publisher holds Copyright.

Download (770kB) | Preview
[img]
Preview
Text
A benchmark of kriging-based infill criteria for noisy optimization.pdf - Accepted Version
Available under License Publisher holds Copyright.

Download (713kB) | Preview

Responses of many real-world problems can only be evaluated perturbed by noise. In order to make an efficient optimization of these problems possible, intelligent optimization strategies successfully coping with noisy evaluations are required. In this article, a comprehensive review of existing kriging-based methods for the optimization of noisy functions is provided. In summary, ten methods for choosing the sequential samples are described using a unified formalism. They are compared on analytical benchmark problems, whereby the usual assumption of homoscedastic Gaussian noise made in the underlying models is meet. Different problem configurations (noise level, maximum number of observations, initial number of observations) and setups (covariance functions, budget, initial sample size) are considered. It is found that the choices of the initial sample size and the covariance function are not critical. The choice of the method, however, can result in significant differences in the performance. In particular, the three most intuitive criteria are found as poor alternatives. Although no criterion is found consistently more efficient than the others, two specialized methods appear more robust on average.

Item Type:

Journal Article (Original Article)

Division/Institute:

08 Faculty of Science > Department of Mathematics and Statistics > Institute of Mathematical Statistics and Actuarial Science

UniBE Contributor:

Ginsbourger, David

Subjects:

500 Science > 510 Mathematics

ISSN:

1615-147X

Publisher:

Springer

Language:

English

Submitter:

Lutz Dümbgen

Date Deposited:

12 Mar 2014 09:25

Last Modified:

05 Dec 2022 14:28

Publisher DOI:

10.1007/s00158-013-0919-4

BORIS DOI:

10.7892/boris.41521

URI:

https://boris.unibe.ch/id/eprint/41521

Actions (login required)

Edit item Edit item
Provide Feedback