Fit a linear model regularized by the nonconvex MC+ sparsity penalty

Description

Sparsenet uses coordinate descent on the MC+ nonconvex penalty family, and fits a surface of solutions over the two-dimensional parameter space.

Details

At its simplest, provide x,y data and it returns the solution paths. There are tools for prediction, cross-validation, plotting and printing.

Author(s)

Rahul Mazumder, Jerome Friedman and Trevor Hastie

Maintainer: Trevor Hastie <hastie@stanford.edu>

References

http://www.stanford.edu/~hastie/Papers/Sparsenet/jasa_MFH_final.pdf

Examples

x=matrix(rnorm(100*20),100,20)
y=rnorm(100)
fit=sparsenet(x,y)
plot(fit)
cvfit=cv.sparsenet(x,y)
plot(cvfit)

Results