Exponential inequalities for VLMC empirical trees.

Abstract : A seminal paper by Rissanen, published in 1983, introduced the class of Variable Length Markov Chains and the algorithm Context which estimates the probabilistic tree generating the chain. Even if the subject was recently considered in several papers, the central question of the rate of convergence of the algorithm remained open. This is the question we address here. We provide an exponential upper bound for the probability of incorrect estimation of the probabilistic tree, as a function of the size of the sample. As a consequence we prove the almost sure consistency of the algorithm Context. We also derive exponential upper bounds for type I errors and for the probability of underestimation of the context tree. The constants appearing in the bounds are all explicit and obtained in a constructive way.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00504020
Contributor : Véronique Maume-Deschamps <>
Submitted on : Monday, July 19, 2010 - 3:54:37 PM
Last modification on : Thursday, February 7, 2019 - 4:32:00 PM

Links full text

Identifiers

Citation

Antonio Galves, Véronique Maume-Deschamps, Bernard Schmitt. Exponential inequalities for VLMC empirical trees.. ESAIM: Probability and Statistics, EDP Sciences, 2008, 12, pp.119. ⟨10.1051/ps:2007035⟩. ⟨hal-00504020⟩

Share

Metrics

Record views

123