Title :
Adaptive encoding and prediction of hidden Markov processes
Author :
Gerencser, L. ; Molnar-Saska, G.
Author_Institution :
MTA SZTAKI, Computer and Automation Institute, Hungarian Academy of Sciences, 13-17 Kende u., Budapest 1111, Hungary
Abstract :
The purpose of this paper is to provide explicit results on the almost sure asymptotic performance of adaptive encoding and prediction procedures for finite-state Hidden Markov Models. In addition, Rissanen´s tail condition [14] will be verified, from which a lower bound for the mean-performance of universal encoding procedures will be derived. The results of this paper are based on [10].
Keywords :
Complexity theory; Encoding; Hidden Markov models; Markov processes; Maximum likelihood estimation; Stochastic systems; Hidden Markov Models; adaptive encoding; adaptive prediction; maximum-likelihood estimation; stochastic complexity;
Conference_Titel :
European Control Conference (ECC), 2003
Conference_Location :
Cambridge, UK
Print_ISBN :
978-3-9524173-7-9
