Fast sampling of parameterised Gaussian random fields
From MaRDI portal
Publication:1987947
Abstract: Gaussian random fields are popular models for spatially varying uncertainties, arising for instance in geotechnical engineering, hydrology or image processing. A Gaussian random field is fully characterised by its mean function and covariance operator. In more complex models these can also be partially unknown. In this case we need to handle a family of Gaussian random fields indexed with hyperparameters. Sampling for a fixed configuration of hyperparameters is already very expensive due to the nonlocal nature of many classical covariance operators. Sampling from multiple configurations increases the total computational cost severely. In this report we employ parameterised Karhunen-Lo`eve expansions for sampling. To reduce the cost we construct a reduced basis surrogate built from snapshots of Karhunen-Lo`eve eigenvectors. In particular, we consider Mat'ern-type covariance operators with unknown correlation length and standard deviation. We suggest a linearisation of the covariance function and describe the associated online-offline decomposition. In numerical experiments we investigate the approximation error of the reduced eigenpairs. As an application we consider forward uncertainty propagation and Bayesian inversion with an elliptic partial differential equation where the logarithm of the diffusion coefficient is a parameterised Gaussian random field. In the Bayesian inverse problem we employ Markov chain Monte Carlo on the reduced space to generate samples from the posterior measure. All numerical experiments are conducted in 2D physical space, with non-separable covariance operators, and finite element grids with degrees of freedom.
Recommendations
- Fast sampling of Gaussian Markov random fields
- Fast simulation of Gaussian random fields
- Sampling Strategies for Fast Updating of Gaussian Markov Random Fields
- Multilevel approximation of Gaussian random fields: fast simulation
- Fast simulation for Gaussian random fields on compact Riemannian manifolds
- Parallel exact sampling and evaluation of Gaussian Markov random fields
- Coarse-grid sampling interpolatory methods for approximating Gaussian random fields
- Fast sampling in a linear-Gaussian inverse problem
- Fast generation of isotropic Gaussian random fields on the sphere
Cites work
- A generalized polynomial chaos-based method for efficient Bayesian calibration of uncertain computational models
- A multilevel, hierarchical sampling technique for spatially correlated random fields
- Accurate solution of Bayesian inverse uncertainty quantification problems combining reduced basis methods and reduction error models
- An Algorithm for Simulating Stationary Gaussian Random Fields
- An implicit restarted Lanczos method for large symmetric eigenvalue problems
- Analysis of Circulant Embedding Methods for Sampling Stationary Random Fields
- Application of hierarchical matrices for computing the Karhunen-Loève expansion
- Certified reduced basis methods for parametrized partial differential equations
- Coarse-grid sampling interpolatory methods for approximating Gaussian random fields
- Coordinate transformation and polynomial chaos for the Bayesian inference of a Gaussian process with parametrized prior covariance function
- Efficient approximation of random fields for numerical applications.
- Fast and Exact Simulation of Stationary Gaussian Processes through Circulant Embedding of the Covariance Matrix
- Fast model updating coupling Bayesian inference and PGD model reduction
- Fast random field generation with \(H\)-matrices
- Fast spatial Gaussian process maximum likelihood estimation via skeletonization factorizations
- Faster computation of the Karhunen-Loève expansion using its domain independence property
- Goal-oriented adaptive surrogate construction for stochastic inversion
- Handbook of uncertainty quantification. In 2 volumes
- Hierarchical Bayesian level set inversion
- scientific article; zbMATH DE number 3731128 (Why is no real title available?)
- scientific article; zbMATH DE number 51414 (Why is no real title available?)
- scientific article; zbMATH DE number 3493825 (Why is no real title available?)
- scientific article; zbMATH DE number 3599198 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- scientific article; zbMATH DE number 782652 (Why is no real title available?)
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- scientific article; zbMATH DE number 3046994 (Why is no real title available?)
- Hyperpriors for Matérn fields with applications in Bayesian inversion
- Inverse problems: a Bayesian perspective
- Karhunen-Loève approximation of random fields by generalized fast multipole methods
- Low-Rank Eigenvector Compression of Posterior Covariance Matrices for Linear Gaussian Inverse Problems
- MCMC methods for functions: modifying old algorithms to make them faster
- Multiscale model reduction method for Bayesian inverse problems of subsurface flow
- Nonintrusive uncertainty analysis of fluid-structure interaction with spatially adaptive sparse grids and polynomial chaos expansion
- Numerical methods for the discretization of random fields by means of the Karhunen-Loève expansion
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Optimal model management for multifidelity Monte Carlo estimation
- Output bounds for reduced-basis approximations of symmetric positive definite eigenvalue problems
- Parallel domain decomposition strategies for stochastic elliptic equations. Part A: Local Karhunen-Loève representations
- Parameter and state model reduction for large-scale statistical inverse problems
- Posterior consistency for Gaussian process approximations of Bayesian posterior distributions
- Randomized algorithms for generalized Hermitian eigenvalue problems with application to computing Karhunen-Loève expansion.
- Reduced basis approximation and a posteriori error estimates for parametrized elliptic eigenvalue problems
- Reduced basis isogeometric mortar approximations for eigenvalue problems in vibroacoustics
- Reduced basis methods for partial differential equations. An introduction
- Scalable hierarchical PDE sampler for generating spatially correlated random fields using nonmatching meshes.
- Sequential Monte Carlo methods for Bayesian elliptic inverse problems
- Simulation of multi-dimensional random fields by Karhunen-Loève expansion
- Simultaneous reduced basis approximation of parameterized elliptic eigenvalue problems
- Sparse approximations of fractional Matérn fields
- Sparse-grid, reduced-basis Bayesian inversion
- Stochastic collocation for elliptic PDEs with random data: the lognormal case
- Strong and weak error estimates for elliptic partial differential equations with random coefficients
- Subspace acceleration for large-scale parameter-dependent Hermitian eigenproblems
- Survey of multifidelity methods in uncertainty propagation, inference, and optimization
- Templates for the Solution of Algebraic Eigenvalue Problems
- The Bayesian Choice
- The ROMES method for statistical modeling of reduced-order-model error
- Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
- Uncertainty quantification. Theory, implementation, and applications
- Weak convergence of Galerkin approximations for fractional elliptic stochastic PDEs with spatial white noise
Cited in
(29)- Bayesian inference of random fields represented with the Karhunen-Loève expansion
- Regularity and convergence analysis in Sobolev and Hölder spaces for generalized Whittle-Matérn fields
- Stochastic field simulation of slope stability problems: improvement and reduction of computational effort
- Fast automatic Bayesian cubature using lattice sampling
- Coordinate transformation and polynomial chaos for the Bayesian inference of a Gaussian process with parametrized prior covariance function
- Fast simulation for Gaussian random fields on compact Riemannian manifolds
- Sampling from Gaussian Markov random fields conditioned on linear constraints
- Sampling Gaussian distributions in Krylov spaces with conjugate gradients
- Parameter expansion for sampling a correlation matrix: an efficient GPX-RPMH algorithm
- Efficient Monte Carlo for high excursions of Gaussian random fields
- On the well-posedness of Bayesian inverse problems
- Multilevel approximation of Gaussian random fields: fast simulation
- Unified Analysis of Periodization-Based Sampling Methods for Matérn Covariances
- Determination of the reaction coefficient in a time dependent nonlocal diffusion process
- Itô SDE-based generator for a class of non-Gaussian vector-valued random fields in uncertainty quantification
- Multilevel adaptive sparse Leja approximations for Bayesian inverse problems
- A multilevel, hierarchical sampling technique for spatially correlated random fields
- Coarse-grid sampling interpolatory methods for approximating Gaussian random fields
- Fast sampling of Gaussian Markov random fields
- Bayesian Inverse Problems Are Usually Well-Posed
- Stochastic PDE representation of random fields for large-scale Gaussian process regression and statistical finite element analysis
- Bayesian inference with subset simulation in varying dimensions applied to the Karhunen-Loève expansion
- Multilevel approximation of Gaussian random fields: covariance compression, estimation, and spatial prediction
- Nesterov acceleration for ensemble Kalman inversion and variants
- Efficient Bayesian inversion for simultaneous estimation of geometry and spatial field using the Karhunen-Loève expansion
- Change of measure for Bayesian field inversion with hierarchical hyperparameters sampling
- Dirichlet-Neumann averaging: the DNA of efficient Gaussian process simulation
- Wavelet compression for sampling deep Gaussian processes
- Quantifying uncertainties on excursion sets under a Gaussian random field prior
This page was built for publication: Fast sampling of parameterised Gaussian random fields
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1987947)
