Penalised spline support vector classifiers: Computational issues

Ormerod, JT; Wand, MP; Koch, I

Penalised spline support vector classifiers: Computational issues

Ormerod, JT Wand, MP

Koch, I

Permalink

Publication Type:: Journal Article
Citation:: Computational Statistics, 2008, 23 (4), pp. 623 - 641
Issue Date:: 2008-10-01

Closed Access

	Filename	Description	Size
	2010000455OK.pdf		317.75 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Ormerod, JT	en_US
dc.contributor.author	Wand, MP https://orcid.org/0000-0003-2555-896X	en_US
dc.contributor.author	Koch, I	en_US
dc.date.issued	2008-10-01	en_US
dc.identifier.citation	Computational Statistics, 2008, 23 (4), pp. 623 - 641	en_US
dc.identifier.issn	0943-4062	en_US
dc.identifier.uri	http://hdl.handle.net/10453/14483
dc.description.abstract	We study computational issues for support vector classification with penalised spline kernels. We show that, compared with traditional kernels, computational times can be drastically reduced in large problems making such problems feasible for sample sizes as large as ~106. The optimisation technology known as interior point methods plays a central role. Penalised spline kernels are also shown to allow simple incorporation of low-dimensional structure such as additivity. This can aid both interpretability and performance. © 2008 Springer-Verlag.	en_US
dc.relation.ispartof	Computational Statistics	en_US
dc.relation.isbasedon	10.1007/s00180-007-0102-8	en_US
dc.subject.classification	Statistics & Probability	en_US
dc.title	Penalised spline support vector classifiers: Computational issues	en_US
dc.type	Journal Article
utslib.citation.volume	4	en_US
utslib.citation.volume	23	en_US
utslib.for	0104 Statistics	en_US
utslib.for	01 Mathematical Sciences	en_US
utslib.for	08 Information and Computing Sciences	en_US
dc.location.activity	Sydney, Australia
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	closed_access
pubs.issue	4	en_US
pubs.publication-status	Published	en_US
pubs.volume	23	en_US

Abstract:

We study computational issues for support vector classification with penalised spline kernels. We show that, compared with traditional kernels, computational times can be drastically reduced in large problems making such problems feasible for sample sizes as large as ~106. The optimisation technology known as interior point methods plays a central role. Penalised spline kernels are also shown to allow simple incorporation of low-dimensional structure such as additivity. This can aid both interpretability and performance. © 2008 Springer-Verlag.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/14483