Exponential inequalities for empirical unbounded context trees

dc.creatorGalves, Antonio
dc.creatorLeonardi, Florencia
dc.date2007-10-31
dc.date2008-05-22
dc.date.accessioned2026-07-07T09:40:03Z
dc.date.available2026-07-07T09:40:03Z
dc.descriptionIn this paper we obtain non-uniform exponential upper bounds for the rate of convergence of a version of the algorithm Context, when the underlying tree is not necessarily bounded. The algorithm Context is a well-known tool to estimate the context tree of a Variable Length Markov Chain. As a consequence of the exponential bounds we obtain a strong consistency result. We generalize in this way several previous results in the field.
dc.description13 pages
dc.identifierhttps://arxiv.org/abs/0710.5900
dc.identifierhttp://arxiv.org/abs/0710.5900
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/161366
dc.subjectStatistics Theory
dc.subjectProbability
dc.subject62M09; 60G99
dc.titleExponential inequalities for empirical unbounded context trees
dc.typetext

Files

Collections