Exponential bounds for convergence of entropy rate approximations in hidden Markov models satisfying a path-mergeability condition
A hidden Markov model (HMM) is said to have path-mergeable states if for any two states i,j there exist a word w and state k such that it is possible to transition from both i and j to k while emitting w. We show that for a finite HMM with path-mergeable states the block estimates of the entropy rate converge exponentially fast. We also show that the path-mergeability property is asymptotically typical in the space of HMM topologies and easily testable.
Year of publication: |
2014
|
---|---|
Authors: | Travers, Nicholas F. |
Published in: |
Stochastic Processes and their Applications. - Elsevier, ISSN 0304-4149. - Vol. 124.2014, 12, p. 4149-4170
|
Publisher: |
Elsevier |
Subject: | Hidden Markov model | Entropy rate | Exponential convergence | Path-mergeable |
Saved in:
Online Resource
Saved in favorites
Similar items by subject
-
Lévy walk in complex networks: An efficient way of mobility
Zhao, Yi, (2014)
-
The Minority Game with interactions
Caridi, Inés, (2004)
-
Monte Carlo methods for mean-risk optimization and portfolio selection
Xu, Huifu, (2012)
- More ...