Please use this identifier to cite or link to this item:
Title: A fast algorithm for non-negativity model selection
Authors: Gatu, Cristian 
Kontoghiorghes, Erricos John 
metadata.dc.contributor.other: Κοντογιώργης, Ερρίκος
Major Field of Science: Social Sciences
Field Category: Economics and Business
Keywords: Branch-and-bound algorithms;Subset selection;Non-negative least squares
Issue Date: 2013
Source: Statistics and Computing, 2013, vol. 23, pp. 403-411
Volume: 23
Start page: 403
End page: 411
Journal: Statistics and Computing 
Abstract: An efficient optimization algorithm for identifying the best least squares regression model under the condition of non-negative coefficients is proposed. The algorithm exposits an innovative solution via the unrestricted least squares and is based on the regression tree and branch-and-bound techniques for computing the best subset regression. The aim is to filling a gap in computationally tractable solutions to the non-negative least squares problem and model selection. The proposed method is illustrated with a real dataset. Experimental results on real and artificial random datasets confirm the computational efficacy of the new strategy and demonstrates its ability to solve large model selection problems that are subject to non-negativity constrains.
ISSN: 09603174
DOI: 10.1007/s11222-012-9318-8
Rights: © Springer
Type: Article
Affiliation : Cyprus University of Technology 
University of Nicosia 
Appears in Collections:Άρθρα/Articles

CORE Recommender
Show full item record


checked on Nov 9, 2023

Page view(s) 50

Last Week
Last month
checked on Jun 19, 2024

Google ScholarTM



Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.