On rate of convergence of statistical estimation of stationary ergodic processes

Authors:
Imre Csiszár;Zsolt Talata
Affiliations:
Department of Mathematics, University of Kansas, Lawrence, KS;Alfréd Rényi Institute of Mathematics, Hungarian Academy of Sciences, Budapest, Hungary
Venue:
IEEE Transactions on Information Theory
Year:
2010

Citing 2
Cited 0

Large-scale typicality of Markov sample paths and consistency of MDL order estimators

IEEE Transactions on Information Theory
Context tree estimation for not necessarily finite memory processes, via BIC and MDL

IEEE Transactions on Information Theory

Quantified Score

Hi-index	754.84

Visualization

Abstract

Stationary ergodic processes with finite alphabets are approximated by finite memory processes based on an n-length realization of the process. Under the assumptions of summable continuity rate and non-nullness, a rate of convergence in d-distance is obtained, with explicit constants. Asymptotically, as n → ∞, the result is near the optimum.