Approximate group context tree

TL;DR

This paper introduces a new efficient method for selecting and estimating variable length Markov chain models shared across multiple processes, with theoretical guarantees and applications to linguistics and dynamic programming.

Contribution

It proposes a novel model selection and estimation approach for group context trees, allowing for model misspecification and providing convergence guarantees.

Findings

Uniform convergence rates for Markov process transition probability estimation

Explicit convergence bounds for chains of infinite order with complete connections

Applicability to linguistic analysis and dynamic programming models

Abstract

We study a variable length Markov chain model associated with a group of stationary processes that share the same context tree but each process has potentially different conditional probabilities. We propose a new model selection and estimation method which is computationally efficient. We develop oracle and adaptivity inequalities, as well as model selection properties, that hold under continuity of the transition probabilities and polynomial $\beta$-mixing. In particular, model misspecification is allowed. These results are applied to interesting families of processes. For Markov processes, we obtain uniform rate of convergence for the estimation error of transition probabilities as well as perfect model selection results. For chains of infinite order with complete connections, we obtain explicit uniform rates of convergence on the estimation of conditional probabilities, which have an explicit dependence on the processes' continuity rates. Similar guarantees are also derived for renewal processes. Our results are shown to be applicable to discrete stochastic dynamic programming problems and to dynamic discrete choice models. We also apply our estimator to a linguistic study, based on recent work, by Galves et al (2012), of the rhythmic differences between Brazilian and European Portuguese.