Scalable iterative methods for sampling from massive Gaussian random vectors
arXiv:1312.1476
Abstract
Sampling from Gaussian Markov random fields (GMRFs), that is multivariate Gaussian ran- dom vectors that are parameterised by the inverse of their covariance matrix, is a fundamental problem in computational statistics. In this paper, we show how we can exploit arbitrarily accu- rate approximations to a GMRF to speed up Krylov subspace sampling methods. We also show that these methods can be used when computing the normalising constant of a large multivariate Gaussian distribution, which is needed for both any likelihood-based inference method. The method we derive is also applicable to other structured Gaussian random vectors and, in particu- lar, we show that when the precision matrix is a perturbation of a (block) circulant matrix, it is still possible to derive O(n log n) sampling schemes.
arXiv comment17 Pages, 4 Figures
References in corpus (6)
- A General Framework for the Parametrization of Hierarchical Models
- On the Numerical Evaluation of Fredholm Determinants
- Slice sampling covariance hyperparameters of latent Gaussian models
- Coupled MCMC with a randomized acceptance probability
- A Hierarchical Multilevel Markov Chain Monte Carlo Algorithm with Applications to Uncertainty Quantification in Subsurface Flow
- Specifying Gaussian Markov Random Fields with Incomplete Orthogonal Factorization using Givens Rotations