Vecchia approximations of Gaussian-process predictions

Abstract

Gaussian processes (GPs) are highly flexible function estimators used for geospatial analysis, nonparametric regression, and machine learning, but they are computationally infeasible for large datasets. Vecchia approximations of GPs have been used to enable fast evaluation of the likelihood for parameter inference. Here, we study Vecchia approximations of spatial predictions at observed and unobserved locations, including obtaining joint predictive distributions at large sets of locations. We consider a general Vecchia framework for GP predictions, which contains some novel and some existing special cases. We study the accuracy and computational properties of these approaches theoretically and numerically, proving that our new methods exhibit linear computational complexity in the total number of spatial locations. We show that certain choices within the framework can have a strong effect on uncertainty quantification and computational cost, which leads to specific recommendations on which methods are most suitable for various settings. We also apply our methods to a satellite dataset of chlorophyll fluorescence, showing that the new methods are faster or more accurate than existing methods, and reduce unrealistic artifacts in prediction maps.

References in corpus (9)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Fast and scalable Gaussian process modeling with applications to astronomical time series
• Flexible and Scalable Methods for Quantifying Stochastic Variability in the Era of Massive Time-Domain Astronomical Data Sets
• A multi-resolution approximation for massive spatial datasets
• Fixed-domain asymptotic properties of tapered maximum likelihood estimators
• Permutation and Grouping Methods for Sharpening Gaussian Process Approximations
• Covariance approximation for large multivariate spatial data sets with an application to multiple climate model errors
• Nonparametric Bayesian Estimation of Periodic Functions
• Spectral Density Estimation for Random Fields via Periodic Embeddings

Cited by in corpus (6)

• A general framework for Vecchia approximations of Gaussian processes
• Vecchia-Laplace approximations of generalized Gaussian processes for big non-Gaussian spatial data
• Correlation-based sparse inverse Cholesky factorization for fast Gaussian-process inference
• Modelling wildland fire burn severity in California using a spatial Super Learner approach
• Iterative Methods for Vecchia-Laplace Approximations for Latent Gaussian Process Models
• Inverse sampling intensity weighting for preferential sampling adjustment