On the inference of applying Gaussian process modeling to a deterministic function
From MaRDI portal
Publication:2074282
Abstract: Gaussian process modeling is a standard tool for building emulators for computer experiments, which are usually used to study deterministic functions, for example, a solution to a given system of partial differential equations. This work investigates applying Gaussian process modeling to a deterministic function from prediction and uncertainty quantification perspectives, where the Gaussian process model is misspecified. Specifically, we consider the case where the underlying function is fixed and from a reproducing kernel Hilbert space generated by some kernel function, and the same kernel function is used in the Gaussian process modeling as the correlation function for prediction and uncertainty quantification. While upper bounds and the optimal convergence rate of prediction in the Gaussian process modeling have been extensively studied in the literature, a comprehensive exploration of convergence rates and theoretical study of uncertainty quantification is lacking. We prove that, if one uses maximum likelihood estimation to estimate the variance in Gaussian process modeling, under different choices of the regularization parameter value, the predictor is not optimal and/or the confidence interval is not reliable. In particular, lower bounds of the prediction error under different choices of the regularization parameter value are obtained. The results indicate that, if one directly applies Gaussian process modeling to a fixed function, the reliability of the confidence interval and the optimality of the predictor cannot be achieved at the same time.
Recommendations
- Maximum likelihood estimation and uncertainty quantification for Gaussian process approximation of deterministic functions
- Gaussian process modeling with boundary information
- Computer emulation with nonstationary Gaussian processes
- Flexible Correlation Structure for Accurate Prediction and Uncertainty Quantification in Bayesian Gaussian Process Emulation of a Computer Model
- Fixed-domain asymptotics of the maximum likelihood estimator and the Gaussian process approach for deterministic models
Cites work
- scientific article; zbMATH DE number 5654889 (Why is no real title available?)
- scientific article; zbMATH DE number 53679 (Why is no real title available?)
- scientific article; zbMATH DE number 3456236 (Why is no real title available?)
- scientific article; zbMATH DE number 6876834 (Why is no real title available?)
- scientific article; zbMATH DE number 7306883 (Why is no real title available?)
- scientific article; zbMATH DE number 2208228 (Why is no real title available?)
- scientific article; zbMATH DE number 5272875 (Why is no real title available?)
- A theoretical framework for calibration in computer models: parametrization, estimation and convergence properties
- An alternative measure of the reliability of ordinary kriging estimates
- An efficient surrogate model for emulation and physics extraction of large eddy simulations
- Asymptotic analysis of covariance parameter estimation for Gaussian processes in the misspecified case
- Asymptotic properties of a maximum likelihood estimator with data from a Gaussian process
- Besov Spaces on Domains in ℝ d
- Cases for the nugget in modeling computer experiments
- Closed form representations and properties of the generalised Wendland functions
- Combining experimental data and computer simulations, with an application to flyer plate experiments
- Composite Gaussian process models for emulating expensive functions
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- Convergence types and rates in generic Karhunen-Loève expansions with applications to sample path properties
- Convex functions and their applications. A contemporary approach
- Credible sets in the fixed design model with Brownian motion prior
- Cross validation and maximum likelihood estimations of hyper-parameters of Gaussian processes with model misspecification
- Estimation and prediction using generalized Wendland covariance functions under fixed domain asymptotics
- Fixed-Domain Asymptotics for Spatial Periodograms
- Gaussian processes for machine learning.
- Geometric and transformational properties of Lipschitz domains, Semmes-Kenig-Toro domains, and other classes of finite perimeter domains
- Inconsistent Estimation and Asymptotically Equal Interpolations in Model-Based Geostatistics
- Interpolation of spatial data -- a stochastic or a deterministic problem?
- Interpolation of spatial data. Some theory for kriging
- Local error estimates for radial basis function interpolation of scattered data
- Maximum Likelihood Estimation for a Smooth Gaussian Random Field Model
- Maximum likelihood estimation and uncertainty quantification for Gaussian process approximation of deterministic functions
- Maximum likelihood estimation of models for residual covariance in spatial regression
- Maximum likelihood estimation of parameters under a spatial sampling scheme
- Multiresolution functional ANOVA for large-scale, many-input computer experiments
- Nonseparable, Stationary Covariance Functions for Space–Time Data
- On Prediction Properties of Kriging: Uniform Error Bounds and Robustness
- On fixed-domain asymptotics and covariance tapering in Gaussian random field models
- On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
- On the consistent separation of scale and variance for Gaussian random fields
- On the efficiency of selection criteria in spline regression
- On the uniform convergence of empirical norms and inner products, with application to causal inference
- Optimal global rates of convergence for nonparametric regression
- Penalized blind kriging in computer experiments
- Single nugget kriging
- Space and space-time modeling using process convolutions
- Spline smoothing with an estimated order parameter
- Stochastic kriging for simulation metamodeling
- Supremum norm posterior contraction and credible sets for nonparametric multivariate regression
- The design and analysis of computer experiments.
- The reproducing kernel Hilbert space structure of the sample paths of a Gaussian process
- The role of the range parameter for estimation and prediction in geostatistics
- Uncertainty quantification in multiscale simulation of woven fiber composites
Cited in
(10)- scientific article; zbMATH DE number 1183932 (Why is no real title available?)
- Error bounds and the asymptotic setting in kernel-based approximation
- A comparative evaluation of stochastic-based inference methods for Gaussian process models
- On estimating the mean function of a Gaussian process
- A Gaussian Process Regression Model for Distribution Inputs
- Solving Fredholm integral equation of the first kind using Gaussian process regression
- Maximum likelihood estimation and uncertainty quantification for Gaussian process approximation of deterministic functions
- The best approximate solution of Fredholm integral equations of the first kind via Gaussian process regression
- Propriety of the reference posterior distribution in Gaussian process modeling
- Identifying the multifractional function of a Gaussian process
This page was built for publication: On the inference of applying Gaussian process modeling to a deterministic function
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2074282)
