Show simple item record  

dc.contributor.authorFrank, Eibe
dc.contributor.authorBouckaert, Remco R.
dc.coverage.spatialConference held at Nanjing, Chinaen_NZ
dc.date.accessioned2010-03-10T20:56:58Z
dc.date.available2010-03-10T20:56:58Z
dc.date.issued2009
dc.identifier.citationFrank, E. & Bouckaert, R. R. (2009). Conditional density estimation with class probability estimators. In E.-H. Zhou & T. Washio (Eds.), Proceedings of First Asian Conference on Machine Learning, ACML 2009, Nanjing, China, November 2-4, 2009. (pp. 65-81). Berlin: Springer.en
dc.identifier.urihttps://hdl.handle.net/10289/3701
dc.description.abstractMany regression schemes deliver a point estimate only, but often it is useful or even essential to quantify the uncertainty inherent in a prediction. If a conditional density estimate is available, then prediction intervals can be derived from it. In this paper we compare three techniques for computing conditional density estimates using a class probability estimator, where this estimator is applied to the discretized target variable and used to derive instance weights for an underlying univariate density estimator; this yields a conditional density estimate. The three density estimators we compare are: a histogram estimator that has been used previously in this context, a normal density estimator, and a kernel estimator. In our experiments, the latter two deliver better performance, both in terms of cross-validated log-likelihood and in terms of quality of the resulting prediction intervals. The empirical coverage of the intervals is close to the desired confidence level in most cases. We also include results for point estimation, as well as a comparison to Gaussian process regression and nonparametric quantile estimation.en
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherSpringeren
dc.rightsThis is an author’s accepted version of an article published in Proceedings of First Asian Conference on Machine Learning, ACML 2009, Nanjing, China, November 2-4, 2009. ©2009 Springer.en
dc.source1st Asian Conference on Machine Learningen_NZ
dc.subjectcomputer scienceen
dc.titleConditional density estimation with class probability estimatorsen
dc.typeConference Contributionen
dc.identifier.doi10.1007/978-3-642-05224-8_7en_NZ
dc.relation.isPartOfProc First Asian Conference on Machine Learning: Advances in Machine Learningen_NZ
pubs.begin-page65en_NZ
pubs.elements-id19170
pubs.end-page81en_NZ
pubs.finish-date2009-11-04en_NZ
pubs.place-of-publicationGermanyen_NZ
pubs.start-date2009-11-02en_NZ
pubs.volumeLNCS 5828en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record