Jewel: A Novel Method for Joint Estimation of Gaussian Graphical Models

In this paper, we consider the problem of estimating multiple Gaussian Graphical Models from high-dimensional datasets. We assume that these datasets are sampled different distributions with same conditional independence structure, but not precision matrix. propose jewel, a joint data estimation method uses node-wise penalized regression approach. particular, jewel group Lasso penalty to simultaneously guarantee resulting adjacency matrix’s symmetry and graphs’ learning. solve minimization using descend algorithm two procedures for regularization parameter. Furthermore, establish estimator’s consistency property. Finally, illustrate our performance through simulated real examples on gene regulatory networks.