Measure Concentration of Hidden Markov Processes

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We prove what appears to be the first concentration of measure result for hidden Markov processes. Our bound is stated in terms of the contraction coefficients of the underlying Markov process, and strictly generalizes the Markov process concentration results of Marton (1996) and Samson (2000). Somewhat surprisingly, the bound turns out to be the same as for ordinary Markov processes; this property, however, fails for general hidden/observed process pairs.
8 pages, 1 figure

Keywords

Probability, Functional Analysis, 60G07; 60J05

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/115256

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/math/0608064
 http://arxiv.org/abs/math/0608064

Collections

arXiv