logoUniv

Università degli Studi di Genova

 


A consistent algorithm to solve Lasso, elastic-net and Tikhonov regularization

Abstract:
In the framework of supervised learning we prove that the iterative algorithm introduced in previous paper allows to estimate in a consistent way the relevant features of the regression function under the a priori assumption that it admits a sparse representation on a fixed dictionary.

Keywords:
Learning theory, Regularization, Sparsity, Consistent estimator

MSC:
60, 49