gif: Graphical Independence Filtering
Provides a method of recovering the precision matrix for Gaussian graphical models efficiently. Our approach could be divided into three categories. First of all, we use Hard Graphical Thresholding for best subset selection problem of Gaussian graphical model, and the core concept of this method was proposed by Luo et al. (2014) <arXiv:1407.7819>. Secondly, a closed form solution for graphical lasso under acyclic graph structure is implemented in our package (Fattahi and Sojoudi (2019) <http://jmlr.org/papers/v20/17-501.html>). Furthermore, we implement block coordinate descent algorithm to efficiently solve the covariance selection problem (Dempster (1972) <doi:10.2307/2528966>). Our package is computationally efficient and can solve ultra-high-dimensional problems, e.g. p > 10,000, in a few minutes.
||R (≥ 3.2)
||Rcpp (≥ 0.12.15), MASS, Matrix
||testthat, knitr, rmarkdown
||Shiyun Lin [aut, cre],
Jin Zhu [aut],
Junxian Zhu [aut],
Xueqin Wang [aut],
||Shiyun Lin <linshy27 at mail2.sysu.edu.cn>
||GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
Please use the canonical form
to link to this page.