Bayesian analysis of hierarchical multi-fidelity codes.

Abstract : This paper deals with the Gaussian process based approximation of a code which can be run at different levels of accuracy. This method, which is a particular case of co-kriging, allows us to improve a surrogate model of a complex computer code using fast approximations of it. In particular, we focus on the case of a large number of code levels on the one hand and on a Bayesian approach when we have two levels on the other hand. The main results of this paper are a new approach to estimate the model parameters which provides a closed form expression for an important parameter of the model (the scale factor), a reduction of the numerical complexity by simplifying the covariance matrix inversion, and a new Bayesian modelling that gives an explicit representation of the joint distribution of the parameters and that is not computationally expensive. A thermodynamic example is used to illustrate the comparison between 2-level and 3-level co-kriging.
Type de document :
Autre publication
This paper deals with the Gaussian process based approximation of a code which can be run at diff.. 2012, pp.RSPA-2011-0742
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00654716
Contributeur : Loic Le Gratiet <>
Soumis le : lundi 24 septembre 2012 - 10:25:01
Dernière modification le : jeudi 27 avril 2017 - 09:46:30
Document(s) archivé(s) le : mardi 25 décembre 2012 - 03:50:12

Fichiers

Main_Document.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00654716, version 2
  • ARXIV : 1112.5389

Collections

INSMI | UPMC | USPC | PMA

Citation

Loic Le Gratiet. Bayesian analysis of hierarchical multi-fidelity codes.. This paper deals with the Gaussian process based approximation of a code which can be run at diff.. 2012, pp.RSPA-2011-0742. 〈hal-00654716v2〉

Partager

Métriques

Consultations de
la notice

255

Téléchargements du document

106