Generalization error bounds in semi-supervised classification under the cluster assumption

Simple item page
dc.creatorRigollet, Philippe
dc.date2006-04-11
dc.date.accessioned2026-07-07T08:07:43Z
dc.date.available2026-07-07T08:07:43Z
dc.descriptionWe consider semi-supervised classification when part of the available data is unlabeled. These unlabeled data can be useful for the classification problem when we make an assumption relating the behavior of the regression function to that of the marginal distribution. Seeger (2000) proposed the well-known "cluster assumption" as a reasonable one. We propose a mathematical formulation of this assumption and a method based on density level sets estimation that takes advantage of it to achieve fast rates of convergence both in the number of unlabeled examples and the number of labeled examples.
dc.identifierhttps://arxiv.org/abs/math/0604233
dc.identifierhttp://arxiv.org/abs/math/0604233
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/131027
dc.subjectStatistics Theory
dc.subjectMachine Learning
dc.titleGeneralization error bounds in semi-supervised classification under the cluster assumption
dc.typetext

Files

Collections

arXiv