A Novel Approach for Estimating Multiple Sparse Precision Matrices Using ℓ0,0 Regularization

We present a novel approach for estimating multiple sparse precision matrices using the ℓ
_0,0
regularization. The multiple precision matrices share some common structures such as the weights or locations of non-zero elements, we are interested in selecting simultaneously elements on each precision matrix as well as across multiple precision matrices. This is referred as bi-level variable selection. The optimization problem can be formulated as DC (Difference of Convex functions) programs to which DC programming and DCA (DC Algorithm) are investigated. The experimental results on both simulated and real datasets demonstrate the efficiency of our algorithms.