eprintid: 1758
rev_number: 5
eprint_status: archive
userid: 6
dir: disk0/00/00/17/58
datestamp: 2013-09-17 08:23:42
lastmod: 2013-09-17 08:23:42
status_changed: 2013-09-17 08:23:42
type: article
metadata_visibility: show
creators_name: Gnecco, Giorgio
creators_name: Sanguineti, Marcello
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
title: On Spectral Windows In Supervised Learning From Data 
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
keywords: Analysis of algorithms; Learning from data; Regularization;
Suboptimal solutions; Empirical error functionals; Probabilistic estimates 
abstract: For Tikhonov regularization in supervised learning from data, the effect on the regularized solution of a joint perturbation of the regression function and the data is investigated. Spectral windows in the finite-sample and population cases are compared via probabilistic estimates of the differences between regularized solutions. 
date: 2010
date_type: published
publication: Information Processing Letters
volume: 110
number: 23
publisher: Elsevier
pagerange: 1031 - 1036
id_number: 10.1016/j.ipl.2010.08.011
refereed: TRUE
issn: 0020-0190
official_url: http://www.sciencedirect.com/science/article/pii/S0020019010002693
citation:   Gnecco, Giorgio and Sanguineti, Marcello  On Spectral Windows In Supervised Learning From Data.  Information Processing Letters, 110 (23).  1031 - 1036.  ISSN 0020-0190      (2010)