Matlab implementation of LASSO, LARS, the elastic net and SPCA

Karl Sjöstrand

AbstractUPDATE: Download the latest code and documentation from

There are a number of interesting variable selection methods available beside the regular forward selection and stepwise selection methods. Such approaches include LASSO (Least Absolute Shrinkage and Selection Operator), least angle regression (LARS) and elastic net (LARS-EN) regression. There also exists a method for calculating principal components with sparse loadings. This software package contains Matlab implementations of these functions. The standard implementations of these functions are available as add-on packages in S-Plus and R.
KeywordsLASSO, LARS, SPCA, Matlab, Elastic Net, Sparse, Sparsity, Variable selection
Year2005    Month June
PublisherInformatics and Mathematical Modelling, Technical University of Denmark, DTU
AddressRichard Petersens Plads, Building 321, DK-2800 Kgs. Lyngby
NoteVersion 2.0
Electronic version(s)[zip]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics

Back  ::  IMM Publications