Sparse Group Lasso Solver
This is the release of R package sglOptim version 1.3.6.
R-package Overview
This package is not intended for direct use, it is a service package for other R packages. If you want to use the optimizer I recommend you do one of the following:
- To make a custom sparse group lasso package (i.e. implement your own loss/objective function) see the GitHub repo Xsgl and documentation therein.
- For fitting linear multiple output models using sparse group lasso see the lsgl R-package.
- For doing multi-class classification using sparse group lasso see the msgl R-package.
- For doing multi-label logistic regression using sparse group lasso see the logitsgl R-package.
For details on the algorithm and more see http://dx.doi.org/10.1016/j.csda.2013.06.004. The loss/objective function must be defined in a C++ module, for more information see Building a Customized Sparse Group Lasso Package.
Installation
Install the released version from CRAN:
install.packages("sglOptim")Install the release candidate from GitHub:
# install.packages("devtools")
devtools::install_github("vincent-dk/sglOptim")Install the development version from GitHub:
# install.packages("devtools")
devtools::install_github("vincent-dk/sglOptim", ref = "develop")License
GPL (>=2)