Stochastic approximation of score functions for Gaussian processes

DOI10.1214/13-AOAS627zbMath1454.62283arXiv1312.2687OpenAlexW3104200791MaRDI QIDQ2443174

Michael L. Stein, Jie Chen, Mihai Anitescu

Publication date: 4 April 2014

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1312.2687

Mathematics Subject Classification ID

Inference from spatial processes (62M30) Gaussian processes (60G15) Applications of statistics to environmental and related topics (62P12) Point estimation (62F10) Stochastic approximation (62L20) Factorial statistical designs (62K15)

Related Items

Covariance tapering for multivariate Gaussian random fields estimation, Partition-Based Nonstationary Covariance Estimation Using the Stochastic Score Approximation, Asymptotic near-efficiency of the ``Gibbs-energy (GE) and empirical-variance estimating functions for fitting Matérn models. - II: accounting for measurement errors via ``Conditional GE mean, Likelihood approximation with hierarchical matrices for large spatial datasets, Fast Estimation of $tr(f(A))$ via Stochastic Lanczos Quadrature, Approximating Spectral Sums of Large-Scale Matrices using Stochastic Chebyshev Approximations, Linear-Cost Covariance Functions for Gaussian Random Fields, Fitting Matérn smoothness parameters using automatic differentiation, Scalable computations for nonstationary Gaussian processes, Fast Spatial Gaussian Process Maximum Likelihood Estimation via Skeletonization Factorizations, Gaussian processes for computer experiments, Fractional stochastic partial differential equation for random tangent fields on the sphere, Needlet approximation for isotropic random fields on the sphere, Multifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data sets, Local inversion-free estimation of spatial Gaussian processes, A case study competition among methods for analyzing large spatial data, Latent Gaussian random field mixture models, Scalable Gaussian Process Computations Using Hierarchical Matrices, How Accurately Should I Compute Implicit Matrix-Vector Products When Applying the Hutchinson Trace Estimator?, Unnamed Item

Uses Software

• Krylstat
• FRK

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Strictly and non-strictly positive definite functions on spheres
• Approximate Bayesian inference for large spatial datasets using predictive process models
• Parameter estimation in high dimensional Gaussian distributions
• Spatial variation of total column ozone on a global scale
• Asymptotic properties of computationally efficient alternative estimators for a class of multivariate normal models
• A modeling approach for large spatial datasets
• The block conjugate gradient algorithm and related methods
• Interpolation of spatial data. Some theory for kriging
• Quasi-likelihood and its application. A general approach to optimal parameter estimation
• Asymptotic comparison of (partial) cross-validation, GCV and randomized GCV in nonparametric regression
• On fixed-domain asymptotics and covariance tapering in Gaussian random field models
• A Matrix-free Approach for Solving the Parametric Gaussian Process Maximum Likelihood Problem
• Difference Filter Preconditioning for Large Covariance Matrices
• Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix
• Computing $f(A)b$ via Least Squares Polynomial Approximations
• Geostatistics
• Fixed-Domain Asymptotics for Spatial Periodograms
• Fixed Rank Kriging for Very Large Spatial Data Sets
• Edge effects and efficient parameter estimation for stationary random fields
• Parameter estimation for a stationary process on a d-dimensional lattice
• Factorized Sparse Approximate Inverse Preconditionings I. Theory
• Approximating Likelihoods for Large Spatial Data Sets
• Matrix Preconditioning Techniques and Applications
• Approximate Likelihood for Large Irregularly Spaced Spatial Data
• Covariance Tapering for Likelihood-Based Estimation in Large Spatial Data Sets
• An Introduction to Iterative Toeplitz Solvers
• Inconsistent Estimation and Asymptotically Equal Interpolations in Model-Based Geostatistics
• A stochastic estimator of the trace of the influence matrix for laplacian smoothing splines
• Variable Selection and Model Building via Likelihood Basis Pursuit
• ON STATIONARY PROCESSES IN THE PLANE
• A fast algorithm for particle simulations