Bayesian adaptive reconstruction of profile optima and optimizers

Abstract : Given a function depending both on decision parameters and nuisance variables, we consider the issue of estimating and quantifying uncertainty on profile optima and/or optimal points as functions of the nuisance variables. The proposed methods base on interpolations of the objective function constructed from a finite set of evaluations. Here the functions of interest are reconstructed relying on a kriging model, but also using Gaussian field conditional simulations, that allow a quantification of uncertainties in the Bayesian framework. Besides, we elaborate a variant of the Expected Improvement criterion, that proves efficient for adaptively learning the set of profile optima and optimizers. The results are illustrated on a toy example and through a physics case study on the optimal packing of polydisperse frictionless spheres.
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger
Contributeur : David Ginsbourger <>
Soumis le : mardi 17 décembre 2013 - 19:05:03
Dernière modification le : lundi 22 octobre 2018 - 15:04:04
Document(s) archivé(s) le : mardi 18 mars 2014 - 05:32:05


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00920154, version 1



David Ginsbourger, Jean Baccou, Clément Chevalier, Frédéric Perales, Nicolas Garland, et al.. Bayesian adaptive reconstruction of profile optima and optimizers. 2013. 〈hal-00920154〉



Consultations de la notice


Téléchargements de fichiers