Nicholas Barnfield, Raphaël Grondin, McGill University, Canada; Gaia Pozzoli, CY Cergy Paris Université, France; Renaud Raquépas, New York University, United States
Session:
Estimation 2
Track:
11: Information Theory and Statistics
Location:
Omikron I
Presentation Time:
Fri, 12 Jul, 16:25 - 16:45
Session Chair:
Andrew Thangaraj,
Abstract
We present a proof of strong consistency of a Ziv–Merhav-type estimator of the cross entropy rate for pairs of hidden-Markov processes. Our proof strategy has two novel aspects: the focus on decoupling properties of the laws and the use of tools from the thermodynamic formalism.