Is margin preserved after random projection?

dc.contributor.authorShi, Q.
dc.contributor.authorShen, C.
dc.contributor.authorHill, R.
dc.contributor.authorVan Den Hengel, A.
dc.contributor.conferenceInternational Conference on Machine Learning (29th : 2012 : Edinburgh, Scotland)
dc.date.issued2012
dc.description.abstractRandom projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this paper we analyse margin distortion after random projection, and give the conditions of margin preservation for binary classification problems. We also extend our analysis to margin for multiclass problems, and provide theoretical bounds on multiclass margin on the projected data.
dc.description.statementofresponsibilityQinfeng Shi, Chunhua Shen, Rhys Hill, Anton van den Hengel
dc.description.urihttp://arxiv.org/html/1207.4676v1
dc.identifier.citationProceedings of the 29th International Conference on Machine Learning, held in Edinburgh, Scotland, UK, 27 June-3 July 2012 / J. Langford and J. Pineau (eds.): pp. 591-598
dc.identifier.isbn9781450312851
dc.identifier.orcidShi, Q. [0000-0002-9126-2107]
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]
dc.identifier.urihttp://hdl.handle.net/2440/71063
dc.language.isoen
dc.publisherOmnipress
dc.publisher.placeUSA
dc.rightsCopyright 2012 by the author(s)/owner(s).
dc.titleIs margin preserved after random projection?
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_71063.pdf
Size:
557.47 KB
Format:
Adobe Portable Document Format
Description:
Accepted version