Show simple item record  

dc.contributor.authorDurrant, Robert J.
dc.contributor.authorKabán, Ata
dc.contributor.editorDasgupta, S
dc.contributor.editorMcAllester, D
dc.coverage.spatialConference held at Atlanta, USA
dc.date.accessioned2014-12-10T00:38:16Z
dc.date.available2013-06-16
dc.date.available2014-12-10T00:38:16Z
dc.date.issued2013
dc.identifier.citationDurrant, R. J., & Kaban, A. (2013). Sharp generalization error bounds for randomly-projected classifiers. In S. Dasgupta & D. McAllester (Eds.), Proceedings of the Thirtieth International Conference on Machine Learning, Atlanta, USA(Vol. JMLR Workshop and Conference Proceedings, Volume 28, p. 693).en
dc.identifier.issn1533-7928
dc.identifier.urihttps://hdl.handle.net/10289/8941
dc.description.abstractWe derive sharp bounds on the generalization error of a generic linear classifier trained by empirical risk minimization on randomly projected data. We make no restrictive assumptions (such as sparsity or separability) on the data: Instead we use the fact that, in a classification setting, the question of interest is really ‘what is the effect of random projection on the predicted class labels?’ and we therefore derive the exact probability of ‘label flipping’ under Gaussian random projection in order to quantify this effect precisely in our bounds .
dc.format.extent693 - 701 (9)
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherJMLR
dc.relation.urihttp://jmlr.org/proceedings/papers/v28/durrant13.pdf
dc.rightsThis is an author’s accepted version of a paper published in the Proceedings of The 30th International Conference on Machine Learning. © 2013 The Authors.
dc.titleSharp generalization error bounds for randomly-projected classifiers
dc.typeConference Contribution
dc.relation.isPartOfProceedings of the Thirtieth International Conference on Machine Learning
pubs.begin-page693
pubs.begin-page701
pubs.elements-id23687
pubs.end-page701en_NZ
pubs.finish-date2013-06-21
pubs.organisational-group/Waikato
pubs.organisational-group/Waikato/FCMS
pubs.organisational-group/Waikato/FCMS/Statistics
pubs.start-date2013-06-16
pubs.volumeJMLR Workshop and Conference Proceedings, Volume 28


Files in this item

This item appears in the following Collection(s)

Show simple item record