Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/17009
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kazakeviciute, A | - |
dc.contributor.author | Kazakevicius, V | - |
dc.contributor.author | Olivo, M | - |
dc.date.accessioned | 2018-10-22T13:39:39Z | - |
dc.date.available | 2017-06-01 | - |
dc.date.available | 2018-10-22T13:39:39Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | IEEE Transactions on Information Theory, 2017, 63 (6), pp. 3425 - 3432 | en_US |
dc.identifier.issn | 0018-9448 | - |
dc.identifier.issn | http://dx.doi.org/10.1109/TIT.2017.2696961 | - |
dc.identifier.uri | http://bura.brunel.ac.uk/handle/2438/17010 | - |
dc.description.abstract | We consider the statistical problem of binary classification, which means attaching a random observation X from a separable metric space E to one of the two classes, 0 or 1. We prove that the consistent estimation of conditional probability p(X)= P(Y=1 X) , where Y is the true class of X, is equivalent to the consistency of a class of empirical classifiers. We then investigate for what classes P there exist an estimate p that is consistent uniformly in p P. We show that this holds if and only if P is a totally bounded subset of L1(Eμ), where μ is the distribution of X. In the case, where E is countable, we give a complete characterization of classes π, allowing consistent estimation of p, uniform in (μ,p)ϵπ. | en_US |
dc.format.extent | 3425 - 3432 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.title | Conditions for Existence of Uniformly Consistent Classifiers | en_US |
dc.type | Article | en_US |
dc.identifier.doi | http://dx.doi.org/10.1109/TIT.2017.2696961 | - |
dc.relation.isPartOf | IEEE Transactions on Information Theory | - |
pubs.issue | 6 | - |
pubs.publication-status | Published | - |
pubs.volume | 63 | - |
Appears in Collections: | Publications Publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Fulltext.pdf | 224.45 kB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.