A greedy algorithm for sparse precision matrix approximation

DOI10.4208/JCM.2005-M2019-0151MaRDI QIDQ6321336arXivFDO

Authors Didi Lv, Xiaoqun Zhang

Publication date 1 July 2019

Published in arXiv

Full work available at URL https://doi.org/10.4208/JCM.2005-M2019-0151

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Numerical linear algebra (65F99) Numerical mathematical programming methods (65K05) Convex programming (90C25) Applications of mathematical programming (90C90)

arXiv classification

math.STstat.TH

Abstract: Precision matrix estimation is an important problem in statistical data analysis. This paper introduces a fast sparse precision matrix estimation algorithm, namely GISS${}^{ho}$, which is originally introduced for compressive sensing. The algorithm GISS${}^{ho}$ is derived based on $l_1$ minimization while with the computation advantage of greedy algorithms. We analyze the asymptotic convergence rate of the proposed GISS${}^{ho}$ for sparse precision matrix estimation and sparsity recovery properties with respect to the stopping criteria. Finally, we numerically compare GISS${}^{ho}$ to other sparse recovery algorithms, such as ADMM and HTP in three settings of precision matrix estimation. The numerical results show the advantages of the proposed algorithm.

This page was built for publication: A greedy algorithm for sparse precision matrix approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6321336)