Volume 12, April 2008
|Page(s)||219 - 229|
|Published online||23 January 2008|
Exponential inequalities for VLMC empirical trees
Instituto de Matemática e Estatística, Universidade de São
Paulo, BP 66281, 05315-970 São Paulo, Brasil; email@example.com
2 Institut de Mathématiques de Bourgogne, BP 47870, 21078 Dijon cedex France; firstname.lastname@example.org; email@example.com
Revised: 10 June 2007
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.
Mathematics Subject Classification: 62M05 / 60G99
Key words: Variable Length Markov Chain / context tree / algorithm context / weak dependance
© EDP Sciences, SMAI, 2008
Initial download of the metrics may take a while.