Parameter estimation in high dimensional Gaussian distributions

Erlend Aune, Daniel P. Simpson, Jo Eidsvik

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)

Abstract

In order to compute the log-likelihood for high dimensional Gaussian models, it is necessary to compute the determinant of the large, sparse, symmetric positive definite precision matrix. Traditional methods for evaluating the log-likelihood, which are typically based on Cholesky factorisations, are not feasible for very large models due to the massive memory requirements. We present a novel approach for evaluating such likelihoods that only requires the computation of matrix-vector products. In this approach we utilise matrix functions, Krylov subspaces, and probing vectors to construct an iterative numerical method for computing the log-likelihood.
Original languageEnglish
Pages (from-to)247-263
JournalStatistics and Computing
Volume24
Issue number2
DOIs
Publication statusPublished - Mar 2014

Fingerprint Dive into the research topics of 'Parameter estimation in high dimensional Gaussian distributions'. Together they form a unique fingerprint.

Cite this