Difdtl (version 2.0)

L1_dts: The algorithm used to calculate the difference of two precision matrices estimation.

Description

Calculate the difference of two precision matrices estimation, given the sample covariance matrices of two sample classes.

Usage

L1_dts(SigmaX, SigmaY, rho, lambda)

Arguments

SigmaX

A pXp matrix.

SigmaY

A pXp matrix.

rho

The parameter used in augmented Lagrange method.

lambda

The tuning parameter of lasso penalty.

Value

A symmetric pXp matrix.

References

Huili Yuan, Ruibin Xi and Minghua Deng(2015). Differential Network Analysis via the Lasso Penalized D-Trace Loss. http://arxiv.org/abs/1511.09188

Examples

##generate samples
library(MASS)
set.seed(1);
Sigma1 = genp(50,0.2,0.5)
set.seed(1);
Sigma2 = Sigma1+genp1(50,100,0.5)
tdelta = Sigma2-Sigma1
SigmaX<-solve(Sigma1)
SigmaY<-solve(Sigma2)
n<-200
p<-50
X1<-mvrnorm(n,rep(0,p),SigmaX)
Y1<-mvrnorm(n,rep(0,p),SigmaY)
##use of L1_dts
dtsmatrix<-L1_dts(SigmaX, SigmaY,1,0.5)