Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4608889 | Journal of Complexity | 2011 | 13 Pages |
Abstract
In the framework of supervised learning, we prove that the iterative algorithm introduced in Umanità and Villa (2010) [22] allows us 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.
Related Topics
Physical Sciences and Engineering
Mathematics
Analysis
Authors
Ernesto De Vito, Veronica Umanità , Silvia Villa,