Retour

G-2013-109

Generalized Elastic Net Regression

, et

référence BibTeX

This work presents a variation of the elastic net penalization method. We propose applying a combined \(l\)1 and \(l\)2 norm penalization on a linear combination of regression parameters. This approach is an alternative to the \(l\)1-penalization for variable selection, but takes care of the correlation between the linear combination of parameters. We devise a path algorithm fitting method similar to the one proposed for the least angle regression. Furthermore, a one-shot estimation technique of \(l\)2 regularization parameter is proposed as an alternative to cross-validation. A simulation study is conducted to check the validity of the new technique.

, 10 pages

Publication

Generalized elastic net regression
, et
JSM Proceedings, 3457–3464, 2013 référence BibTeX