gcdnet: LASSO and (adaptive) Elastic-Net penalized least squares, logistic regression, HHSVM and squared hinge loss SVM using a fast GCD algorithm

This package implements a generalized coordinate descent (GCD) algorithm for computing the solution path of the hybrid Huberized support vector machine (HHSVM) and its generalization, including the elastic net penalized least squares, the elastic net penalized SVM with the squared hinge loss and the elastic net penalized logistic regression.

Version: 1.0.4
Depends: Matrix
Published: 2013-11-19
Author: Yi Yang, Hui Zou
Maintainer: Yi Yang <yiyang at umn.edu>
License: GPL-2
URL: http://code.google.com/p/gcdnet/
NeedsCompilation: yes
Materials: ChangeLog
CRAN checks: gcdnet results


Reference manual: gcdnet.pdf
Package source: gcdnet_1.0.4.tar.gz
Windows binaries: r-devel: gcdnet_1.0.4.zip, r-release: gcdnet_1.0.4.zip, r-oldrel: gcdnet_1.0.4.zip
OS X Mavericks binaries: r-release: gcdnet_1.0.4.tgz, r-oldrel: gcdnet_1.0.4.tgz
Old sources: gcdnet archive