Efficient sequential experimental design for surrogate modeling of nested codes

DOI10.1051/PS/2018011zbMATH Open1420.62355arXiv1712.01620OpenAlexW2963497073WikidataQ129752132 ScholiaQ129752132MaRDI QIDQ4967799FDOQ4967799

Authors: Sophie Marque-Pucheu, G. Perrin, Josselin Garnier 

Publication date: 11 July 2019

Published in: ESAIM: Probability and Statistics (Search for Journal in Brave)

Abstract: Thanks to computing power increase, the certification and the conception of complex systems relies more and more on simulation. To this end, predictive codes are needed, which have generally to be evaluated in a huge number of input points. When the computational cost of these codes is high, surrogate models are introduced to emulate the response of these codes. In this paper, we consider the situation when the system response can be modeled by two nested computer codes. By two nested computer codes, we mean that some inputs of the second code are outputs of the first code. More precisely, the idea is to propose sequential designs to improve the accuracy of the nested code's predictor by exploiting the nested structure of the codes. In particular, a selection criterion is proposed to allow the modeler to choose the code to call, depending on the expected learning rate and the computational cost of each code. The sequential designs are based on the minimization of the prediction variance, so adaptations of the Gaussian process formalism are proposed for this particular configuration in order to quickly evaluate the mean and the variance of the predictor. The proposed methods are then applied to examples.

Full work available at URL: https://arxiv.org/abs/1712.01620

Recommendations

• An efficient dimension reduction for the Gaussian process emulation of two nested codes with functional outputs
• Gaussian Process Regression on Nested Spaces
• Adaptive numerical designs for the calibration of computer codes
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Nested polynomial trends for the improvement of Gaussian process-based predictors

zbMATH Keywords

computer experimentssequential designGaussian processuncertainty quantificationsurrogate modelBayesian formalismnested computer codesprediction mean

Mathematics Subject Classification ID

Gaussian processes (60G15) Sequential statistical design (62L05) Inference from stochastic processes and prediction (62M20)

Cites Work

• The Bayesian Choice
• Interpolation of spatial data. Some theory for kriging
• The design and analysis of computer experiments.
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Bayesian calibration of computer models. (With discussion)
• Gaussian processes for machine learning.
• Objective Bayesian Analysis of Spatially Correlated Data
• Cases for the nugget in modeling computer experiments
• Default priors for Gaussioan processes
• Title not available (Why is that?)
• A nonstationary space-time Gaussian process model for partially converged simulations
• Sequential design of computer experiments for the estimation of a probability of failure
• Sequential design for ranking response surfaces
• Title not available (Why is that?)
• Predicting the output from a complex computer code when fast approximations are available
• Cross validation and maximum likelihood estimations of hyper-parameters of Gaussian processes with model misspecification
• Assessment of uncertainty in computer experiments from universal to Bayesian kriging
• Computational intelligence in expensive optimization problems
• RECURSIVE CO-KRIGING MODEL FOR DESIGN OF COMPUTER EXPERIMENTS WITH MULTIPLE LEVELS OF FIDELITY
• Regression and Kriging metamodels with their experimental designs in simulation: a review
• Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling
• Bayesian analysis of hierarchical multifidelity codes
• Nested polynomial trends for the improvement of Gaussian process-based predictors
• A repulsion-based method for the definition and the enrichment of optimized space filling designs in constrained input spaces

Cited In (4)

• Adaptive experimental design for multi‐fidelity surrogate modeling of multi‐disciplinary systems
• Reweighting samples under covariate shift using a Wasserstein distance criterion
• Gaussian Process Regression on Nested Spaces
• An efficient dimension reduction for the Gaussian process emulation of two nested codes with functional outputs

Uses Software

• AK-MCS

This page was built for publication: Efficient sequential experimental design for surrogate modeling of nested codes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4967799)