Computational Experiments on the Tikhonov Regularization of the Total Least Squares Problem release_yw26vxomxfa4fpnzjxgjasx5p4

by Maziar Salahi, Hossein Zareamoghaddam

Published in Computer Science Journal of Moldova by Institute of Mathematics and Computer Science of the Academy of Sciences of Moldova.

2009   Volume 17, Issue 1(49), p14-25


In this paper we consider finding meaningful solutions of ill-conditioned overdetermined linear systems Ax≈b, where A and b are both contaminated by noise. This kind of problems frequently arise in discretization of certain integral equations. One of the most popular approaches to find meaningful solutions of such systems is the so called total least squares problem. First we introduce this approach and then present three numerical algorithms to solve the resulting fractional minimization problem. In spite of the fact that the fractional minimization problem is not necessarily a convex problem, on all test problems we can get the global optimal solution. Extensive numerical experiments are reported to demonstrate the practical performance of the presented algorithms.
In text/plain format

Archived Files and Locations

application/pdf  170.3 kB
file_t6xmyigorbgmjaebxhrllmawuy (webarchive) (publisher)
Read Archived PDF
Type  article-journal
Stage   published
Year   2009
Language   en ?
Journal Metadata
Open Access Publication
Not in Keepers Registry
ISSN-L:  1561-4042
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 6d69dba8-7291-419f-8eba-d93194b94ac5