Computer experiments with functional inputs and scalar outputs by a norm-based approach

Thomas Muehlenstaedt 1 Jana Fruth 2 Olivier Roustant 3, 4, 5, 6, 7
1 TU - Technische Universität Dortmund [Dortmund]
2 OVGU - Otto-von-Guericke University [Magdeburg]
3 LIMOS - Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes
4 FAYOL-ENSMSE - Département Génie mathématique et industriel
5 Mines Saint-Étienne MSE - École des Mines de Saint-Étienne
6 FAYOL-ENSMSE - Institut Henri Fayol
7 GdR MASCOT-NUM - Méthodes d'Analyse Stochastique des Codes et Traitements Numériques
Abstract : A framework for designing and analyzing computer experiments is presented, which is constructed for dealing with functional and scalar inputs and scalar outputs. For designing experiments with both functional and scalar inputs, a two-stage approach is suggested. The first stage consists of constructing a candidate set for each functional input. During the second stage, an optimal combination of the found candidate sets and a Latin hypercube for the scalar inputs is sought. The resulting designs can be considered to be generalizations of Latin hypercubes. Gaussian process models are explored as metamodel. The functional inputs are incorporated into the Kriging model by applying norms in order to define distances between two functional inputs. We propose the use of B-splines to make the calculation of these norms computationally feasible.
Mots-clés : Maximin design space-filling design Gaussian process
Document type :
Journal articles
Complete list of metadatas
https://hal-emse.ccsd.cnrs.fr/emse-01506232
Contributor : Florent Breuil <>
Submitted on : Wednesday, April 12, 2017 - 9:52:53 AM
Last modification on : Thursday, October 17, 2019 - 12:36:11 PM

Links full text

arxiv

Identifiers

Collections

EMSE | DEMO-ENSMSE | FAYOL-ENSMSE | CNRS | TDS-MACS | PRES_CLERMONT | LIMOS | INSTITUT-TELECOM

Citation

Thomas Muehlenstaedt, Jana Fruth, Olivier Roustant. Computer experiments with functional inputs and scalar outputs by a norm-based approach. Statistics and Computing, Springer Verlag (Germany), 2017, 27 (4), pp.1083 - 1097. ⟨10.1007/s11222-016-9672-z⟩. ⟨emse-01506232⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

456

Contact

Informations

CCSD