To solve the unconstrained problem, R is Sigmahat. To solve constrained problem, R is the current partial residual (excluding A terms).
1  subdiag.thresh(R, lam, w = NULL)

R 
pbyp symmetric matrix 
lam 
Nonnegative penalty parameter. Controls sparsity level. 
w 

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.