Support and Quantile Tubes

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

This correspondence studies an estimator of the conditional support of a distribution underlying a set of i.i.d. observations. The relation with mutual information is shown via an extension of Fano's theorem in combination with a generalization bound based on a compression argument. Extensions to estimating the conditional quantile interval, and statistical guarantees on the minimal convex hull are given.

Keywords

Information Theory, Machine Learning

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/134018

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cs/0703055
 http://arxiv.org/abs/cs/0703055

Collections

arXiv