ℋ-matrix techniques for approximating large covariance matrices and estimating its parameters

Alexander Litvinenko, Marc G. Genton, Ying Sun, David E. Keyes

Research output: Contribution to journalArticlepeer-review

Abstract

In this work the task is to use the available measurements to estimate unknown hyper-parameters (variance, smoothness parameter and covariance length) of the covariance function. We do it by maximizing the joint log-likelihood function. This is a non-convex and non-linear problem. To overcome cubic complexity in linear algebra, we approximate the discretised covariance function in the hierarchical (ℋ-) matrix format. The ℋ-matrix format has a log-linear computational cost and storage O(knlogn), where rank k is a small integer. On each iteration step of the optimization procedure the covariance matrix itself, its determinant and its Cholesky decomposition are recomputed within ℋ-matrix format. (© 2016 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)
Original languageEnglish (US)
Pages (from-to)731-732
Number of pages2
JournalPAMM
Volume16
Issue number1
DOIs
StatePublished - Oct 25 2016

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: Alexander Litvinenko and his research work reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST), SRI UQ and ECRC Centers.

Fingerprint

Dive into the research topics of 'ℋ-matrix techniques for approximating large covariance matrices and estimating its parameters'. Together they form a unique fingerprint.

Cite this