High-Dimensional Penalized Regression

Algorithms for lasso and fused-lasso problems: implementation of the lars algorithm for lasso and fusion penalization and EM-based algorithms for (logistic) lasso and fused-lasso penalization.


News

Version 0.93.2 (19-01-2018)

  • c++ warnings correction
  • register routines

Version 0.93.1 (26-01-2016)

  • Documentation correction
  • Add listToMatrix function
  • Optimisation of plot function
  • Change SUPPORT_OPENMP in _OPENMP

Version 0.93 (03-10-2015)

  • stabilization and acceleration of the EM algorithms
  • EM part of the package using 0 based stk++ arrays
  • HDPenReg now based on rtkore

Version 0.92 (03-09-2015)

  • change in c++ code to follow rtkpp 0.9.2

Version 0.91 (25-11-2014)

  • HDPenReg now depends on rtkpp

Version 0.90.1 (21-11-2014)

  • update description in DESCRIPTION
  • change predict in predict.LarsPath to suppress warnings when loading

Version 0.90 (23-10-2014)

  • Add cross-validation on lambda values in HDcvlars
  • Change ouput parameter name "fraction" in "minIndex" in HDcvlars
  • Change plotCv in plot (to follow generic function name)
  • Change HDpredict in predict (to follow generic function name)
  • Overload of coef generic function. coef combines computeCoefficients and coeff function

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("HDPenReg")

0.93.2 by Quentin Grimonprez, a year ago


Browse source code at https://github.com/cran/HDPenReg


Authors: Quentin Grimonprez [aut, cre] , Serge Iovleff [aut]


Documentation:   PDF Manual  


GPL (>= 2) license


Imports methods, Matrix

Depends on rtkore

Linking to rtkore, Rcpp

System requirements: GNU make


See at CRAN