On estimation of surrogate models for multivariate computer experiments
Autor: | Adam Krzyżak, Felix Heimrich, Michael Kohler, Benedikt Bauer |
---|---|
Rok vydání: | 2017 |
Předmět: |
Statistics and Probability
Variables Artificial neural network media_common.quotation_subject 05 social sciences Context (language use) Computer experiment 01 natural sciences Nonparametric regression 010104 statistics & probability Rate of convergence 0502 economics and business Econometrics Applied mathematics 0101 mathematics 050205 econometrics Curse of dimensionality Mathematics media_common Quantile |
Zdroj: | Annals of the Institute of Statistical Mathematics. 71:107-136 |
ISSN: | 1572-9052 0020-3157 |
DOI: | 10.1007/s10463-017-0627-8 |
Popis: | Estimation of surrogate models for computer experiments leads to nonparametric regression estimation problems without noise in the dependent variable. In this paper, we propose an empirical maximal deviation minimization principle to construct estimates in this context and analyze the rate of convergence of corresponding quantile estimates. As an application, we consider estimation of computer experiments with moderately high dimension by neural networks and show that here we can circumvent the so-called curse of dimensionality by imposing rather general assumptions on the structure of the regression function. The estimates are illustrated by applying them to simulated data and to a simulation model in mechanical engineering. |
Databáze: | OpenAIRE |
Externí odkaz: |