sglOptim: Sparse group lasso generic optimizer

Fast generic solver for sparse group lasso optimization problems. The loss (objective) function must be defined in a C++ module. This package apply template metaprogramming techniques, therefore -- when compiling the package from source -- a high level of optimization is needed to gain full speed (e.g. for the GCC compiler use -O3). Use of multiple processors for cross validation and subsampling is supported through OpenMP. The Armadillo C++ library is used as the primary linear algebra engine. (The sglOptim package version a.b.c.d is interpreted as follows: a - primary version, b - major updates and fixes, c - source revision as corresponding to R-Forge, d - minor fixes made only to the CRAN branch of the source)

install.packages("sglOptim", repos="http://R-Forge.R-project.org")

Try the sglOptim package in your browser