Conditional optimization of a noisy function using a kriging metamodel

Sambakhe Diariétou, Rouan Lauriane, Bacro Jean-Noël, Gozé Eric. 2019. Conditional optimization of a noisy function using a kriging metamodel. Journal of Global Optimization, 73 (3) : 615-636.

Url - autres données associées : https://CRAN.R-project.org/package=lhs

Quartile : Q1, Sujet : MATHEMATICS, APPLIED / Quartile : Q3, Sujet : OPERATIONS RESEARCH & MANAGEMENT SCIENCE

Résumé : The efficient global optimization method is popular for the global optimization of computer-intensive black-box functions. Extensions exist, either for the optimization of noisy functions, or for the conditional optimization of deterministic functions, i.e. the search for the values of a subset of parameters that optimize the function conditionally to the values taken by another subset, which are fixed. A metaphor for conditional optimization is the search for a crest line. No method has yet been developed for the conditional optimization of noisy functions: this is what we propose in this article. Testing this new method on test functions showed that, in the case of a high level of noise on the function, the PEQI criterion that we propose is better than the PEI criterion usually implemented in such a situation.

Mots-clés libres : Crest line, Gaussian process, Sampling criterion, Sequential design, Noisy function

Classification Agris : U10 - Informatique, mathématiques et statistiques
U50 - Sciences physiques et chimie

Champ stratégique Cirad : CTS 7 (2019-) - Hors champs stratégiques

Auteurs et affiliations

• Sambakhe Diariétou, CIRAD-PERSYST-UPR AIDA (FRA) - auteur correspondant
• Rouan Lauriane, CIRAD-BIOS-UMR AGAP (FRA)
• Bacro Jean-Noël, UM2 (FRA)
• Gozé Eric, CIRAD-PERSYST-UPR AIDA (FRA) ORCID: 0000-0001-9121-7835

Source : Cirad-Agritrop (https://agritrop.cirad.fr/590403/)

Métriques

[ Page générée et mise en cache le 2024-12-18 ]