Unified Analysis of Periodization-Based Sampling Methods for Matérn Covariances
From MaRDI portal
Abstract: The periodization of a stationary Gaussian random field on a sufficiently large torus comprising the spatial domain of interest is the basis of various efficient computational methods, such as the classical circulant embedding technique using the fast Fourier transform for generating samples on uniform grids. For the family of Mat'ern covariances with smoothness index and correlation length , we analyse the nonsmooth periodization (corresponding to classical circulant embedding) and an alternative procedure using a smooth truncation of the covariance function. We solve two open problems: the first concerning the -dependent asymptotic decay of eigenvalues of the resulting circulant in the nonsmooth case, the second concerning the required size in terms of , of the torus when using a smooth periodization. In doing this we arrive at a complete characterisation of the performance of these two approaches. Both our theoretical estimates and the numerical tests provided here show substantial advantages of smooth truncation.
Recommendations
- Component covariance analysis for periodically correlated random processes
- Covariance Matrix Estimation With Heterogeneous Samples
- On the spectrum of sample covariance matrices for time series
- scientific article; zbMATH DE number 1833045
- RANDOM SAMPLING ESTIMATION FOR ALMOST PERIODICALLY CORRELATED PROCESSES
- Bounds for Estimation of Covariance Matrices From Heterogeneous Samples
- Statistical analysis of the moving least-squares method with unbounded sampling
- Estimation of Covariance Matrices in Unbalanced Random and Mixed Multivariate Models
Cites work
- An introduction to computational stochastic PDEs
- Analysis of Circulant Embedding Methods for Sampling Stationary Random Fields
- Circulant embedding with QMC: analysis for elliptic PDE with lognormal coefficients
- Efficient approximation of random fields for numerical applications.
- Fast and Exact Simulation of Stationary Gaussian Processes through Circulant Embedding of the Covariance Matrix
- Fast random field generation with \(H\)-matrices
- Fast sampling of parameterised Gaussian random fields
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- Quasi-Monte Carlo finite element methods for elliptic PDEs with lognormal random coefficients
- Quasi-Monte Carlo methods for elliptic PDEs with random coefficients and applications
- Representations of Gaussian random fields and approximation of elliptic PDEs with lognormal coefficients
- Sparse polynomial approximation of parametric elliptic PDEs. II: Lognormal coefficients.
Cited in
(6)- Initialization of the circulant embedding method to speed up the generation of Gaussian random fields
- Multilevel Quasi Monte Carlo Methods for Elliptic PDEs with Random Field Coefficients via Fast White Noise Sampling
- Analysis of Boundary Effects on PDE-Based Sampling of Whittle--Matérn Random Fields
- Smoothed circulant embedding with applications to multilevel Monte Carlo methods for PDEs with random coefficients
- Multilevel representations of random fields and sparse approximations of solutions to random PDEs
- Dirichlet-Neumann averaging: the DNA of efficient Gaussian process simulation
This page was built for publication: Unified Analysis of Periodization-Based Sampling Methods for Matérn Covariances
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5130585)
