The Open UniversitySkip to content
 

The ℓ1 oblique procrustes problem

Trendafilov, Nickolay and Watson, G.A (2004). The ℓ1 oblique procrustes problem. Statistics and Computing, 14(1) pp. 39–51.

DOI (Digital Object Identifier) Link: http://dx.doi.org/10.1023/B:STCO.0000009415.14785.2a
Google Scholar: Look up in Google Scholar

Abstract

In this paper, we reconsider the well-known oblique Procrustes problem where the usual least-squares objective function is replaced by a more robust discrepancy measure, based on the ℓ1 norm or smooth approximations of it. We propose two approaches to the solution of this problem. One approach is based on convex analysis and uses the structure of the problem to permit a solution to the ℓ1 norm problem. An alternative approach is to smooth the problem by working with smooth approximations to the ℓ1 norm, and this leads to a solution process based on the solution of ordinary differential equations on manifolds. The general weighted Procrustes problem (both orthogonal and oblique) can also be solved by the latter approach. Numerical examples to illustrate the algorithms which have been developed are reported and analyzed.

Item Type: Journal Article
Copyright Holders: 2004 Kluwer Academic Publishers
ISSN: 1573-1375
Keywords: fitting configurations; constrained optimization; dynamical system on manifolds; descent flows; optimality conditions; reference-structure;factor-pattern
Academic Unit/Department: Mathematics, Computing and Technology > Mathematics and Statistics
Item ID: 28340
Depositing User: Sarah Frain
Date Deposited: 16 Mar 2011 10:56
Last Modified: 16 Mar 2011 10:57
URI: http://oro.open.ac.uk/id/eprint/28340
Share this page:

Altmetrics

Scopus Citations

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk