eprintid: 1713
rev_number: 6
eprint_status: archive
userid: 46
dir: disk0/00/00/17/13
datestamp: 2013-09-13 10:17:39
lastmod: 2013-09-16 12:03:00
status_changed: 2013-09-13 10:17:39
type: article
metadata_visibility: show
creators_name: Gnecco, Giorgio
creators_name: Sanguineti, Marcello
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
title: Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
abstract: Various regularization techniques are investigated in supervised learning from data. Theoretical features of the associated optimization problems are studied, and sparse suboptimal solutions are searched for. Rates of approximate optimization are estimated for sequences of suboptimal solutions formed by linear combinations of n-tuples of computational units, and statistical learning bounds are derived. As hypothesis sets, reproducing kernel Hilbert spaces and their subsets are considered.
date: 2010
date_type: published
publication: Neural Computation
volume: 22
number: 3
publisher: MIT Press
pagerange: 793-829
id_number: 10.1162/neco.2009.05-08-786
refereed: TRUE
issn: 0899-7667
official_url: http://dx.doi.org/10.1162/neco.2009.05-08-786
citation:   Gnecco, Giorgio and Sanguineti, Marcello  Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data.  Neural Computation, 22 (3).  pp. 793-829.  ISSN 0899-7667      (2010)