|
TITLE: Analyticity of Hidden Markov Chains
SPEAKER: Guangyue Han, University of British Columbia
DATE: 2:00 - 3:00 P.M., Friday May 27, 2005
LOCATION: Tioga, 3U (PA)
HOST: Vinay Deolalikar
ABSTRACT:
We prove that under mild assumptions a hidden Markov chain varies analytically,
in a strong sense, as a function of the underlying Markov chain parameters. In
particular, we show that, under these assumptions, the entropy rate of a hidden
Markov chain is an analytic function of the parameters. We give examples to show
how this can fail in degenerate cases. And we study two natural special classes
of hidden Markov chains in more detail: binary hidden Markov chains with an
unambiguous symbol and binary Markov chains corrupted by binary symmetric noise.
|
|
|
printable version
