Mathematics – Statistics Theory
Scientific paper
2010-11-10
Mathematics
Statistics Theory
Scientific paper
The present paper investigates non-asymptotic properties of two popular procedures of context tree (or Variable Length Markov Chains) estimation: Rissanen's algorithm Context and the Penalized Maximum Likelihood criterion. First showing how they are related, we prove finite horizon bounds for the probability of over- and under-estimation. Concerning overestimation, no boundedness or loss-of-memory conditions are required: the proof relies on new deviation inequalities for empirical probabilities of independent interest. The underestimation properties rely on loss-of-memory and separation conditions of the process. These results improve and generalize the bounds obtained previously. Context tree models have been introduced by Rissanen as a parsimonious generalization of Markov models. Since then, they have been widely used in applied probability and statistics.
Garivier Aurelien
Leonardi Florencia
No associations
LandOfFree
Context Tree Selection: A Unifying View does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Context Tree Selection: A Unifying View, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Context Tree Selection: A Unifying View will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-614152