Glmnet for Matlab

      Lasso (L1) and elastic-net regularized generalized linear models
        


Extremely efficient procedures for fitting the entire lasso or elastic-net regularization path for linear regression, logistic and multinomial regression models.

The algorithm uses cyclical coordinate descent in a pathwise fashion, as described in the paper:

Regularized Paths for Generalized Linear Models via Coordinate Descent (Journal of Statistical Software 33(1), 2010) and the paper:

Pathwise coordinate optimization, The Annals of Applied Statistics. Volume 1, Number 2 (2007), 302-332



Algorithm designed by Jerome Friedman, Trevor Hastie and Rob Tibshirani. Fortran code written by Jerome Friedman

MATLAB wrapper written and maintained by Hui Jiang, jiangh@stanford.edu
Department of Statistics, Stanford University, Stanford, California, USA.

Balasubramanian Narasimhan also provided essential help in the Matlab implementation. Eugene Tsyrklevich made the 64-bit build of glmnet on Windows XP.

The distribution in the file glmnet_matlab.zip (available below) contains a dll for Windows XP (tested with Matlab R13) and Windows Vista (tested with Matlab R14), a 64-bit Linux version (tested with Matlab R2008b), and a 64-bit build of glmnet on Windows XP (tested on Matlab R2009a and R2010a). We may add precompiled versions for other platforms such as 32 bit Linux in the future. For now, users of those platforms can easily compile the code themselves.




Download