GGLasso - a Python package for General Graphical Lasso computation

We introduce GGLasso, a Python package for solving General Graphical Lasso problems. The scheme, introduced by (Friedman 2007) (see also (Yuan 2007; Banerjee 2008)), estimates sparse inverse covariance matrix $\Theta$ from multivariate Gaussian data $\mathcal{X} \sim \mathcal{N}(\mu, \Sigma) \in \mathbb{R}^p$. Originally proposed (Dempster 1972) under the name Covariance Selection, this estimation framework has been extended to include latent variables in (Chandrasekaran 2012). Recent extensions joint of multiple matrices, see, e.g., (Danaher 2013; Tomasi 2018). GGLasso contains methods general problem formulation, including important special cases, such as, single (latent variable) Lasso, Group, and Fused Lasso.