Large Deviation Bounds for Functionals of Viterbi Paths

• Published in: IEEE transactions on information theory Vol. 57; no. 6; pp. 3932 - 3937
• Main Authors: Ghosh, A P, Kleiman, E, Roitershtein, A
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.06.2011; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Coding, codes; Convex functions; Estimating techniques; Exact sciences and technology; Hidden Markov models; Information theory; Information, signal and communications theory; large deviations; Limiting; Markov analysis; Markov processes; Mathematical functions; maximum a posteriori path estimator; Optimization algorithms; Random variables; regenerative processes; Signal and communications theory; Speech recognition; Stochastic models; Telecommunications and information theory; Viterbi algorithm; large deviations; Stochastic model; Probabilistic approach; Regenerative process; Stochastic process; Large deviation; Markov chain; Viterbi code; Viterbi algorithm; Hidden Markov models; regenerative processes; A posteriori estimation; Discrete time; maximum a posteriori path estimator
• ISSN: 0018-9448; 1557-9654
• DOI: 10.1109/TIT.2011.2132550

In a number of applications, the underlying stochastic process is modeled as a finite-state discrete-time Markov chain that cannot be observed directly and is represented by an auxiliary process. The maximum a posteriori (MAP) estimator is widely used to estimate states of this hidden Markov model through available observations. The MAP path estimator based on a finite number of observations is calculated by the Viterbi algorithm, and is often referred to as the Viterbi path. It was recently shown in, and, (see also and) that under mild conditions, the sequence of estimators of a given state converges almost surely to a limiting regenerative process as the number of observations approaches infinity. This in particular implies a law of large numbers for some functionals of hidden states and finite Viterbi paths. The aim of this paper is to provide the corresponding large deviation estimates.