liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Piecewise Linear Solution Paths with Application to Direct Weight Optimization
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
2008 (English)In: Automatica, ISSN 0005-1098, Vol. 44, no 11, 2745-2753 p.Article in journal (Refereed) Published
Abstract [en]

Recently, pathfollowing algorithms for parametric optimization problems with piecewise linear solution paths have been developed within the field of regularized regression. This paper presents a generalization of these algorithms to a wider class of problems. It is shown that the approach can be applied to the nonparametric system identification method, Direct Weight Optimization (DWO), and be used to enhance the computational efficiency of this method. The most important design parameter in the DWO method is a parameter (lambda) controlling the bias-variance trade-off, and the use of parametric optimization with piecewise linear solution paths means that the DWO estimates can be efficiently computed for all values of lambda simultaneously. This allows for designing computationally attractive adaptive bandwidth selection algorithms. One such algorithm for DWO is proposed and demonstrated in two examples.

Place, publisher, year, edition, pages
Elsevier, 2008. Vol. 44, no 11, 2745-2753 p.
Keyword [en]
Parametric programming, Piecewise quadratic programming, Function approximation, Nonlinear system identification, Nonparametric identification
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-16240DOI: 10.1016/j.automatica.2008.03.020OAI: diva2:133501
Available from: 2009-01-12 Created: 2009-01-09 Last updated: 2013-07-22

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Roll, Jacob
By organisation
Automatic ControlThe Institute of Technology
In the same journal
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 116 hits
ReferencesLink to record
Permanent link

Direct link