Tweet
PHYSICS: DATA FROM A.E. ALLAHVERDYAN ET AL PROVIDE NEW INSIGHTS INTO PHYSICS
Science Letter
December 16, 2008
"Hidden Markov Processes (HMP) is one of the basic tools of the modern
probabilistic modeling. The characterization of their entropy remains
however an open problem," scientists in Yerevan, Armenia report
(see also Physics).
"Here the entropy of HMP is calculated via the cycle expansion of
the zeta-function, a method adopted from the theory of dynamical
systems. For a class of HMP this method produces exact results both for
the entropy and the moment-generating function. The latter allows to
estimate, via the Chernoff bound, the probabilities of large deviations
for the HMP," wrote A.E. Allahverdyan and colleagues.
The researchers concluded: "More generally, the method offers a
representation of the moment-generating function and of the entropy
via convergent series."
Allahverdyan and colleagues published their study in the Journal of
Statistical Physics (Entropy of Hidden Markov Processes via Cycle
Expansion. Journal of Statistical Physics, 2008;133(3):535-564).
For more information, contact A.E. Allahverdyan, Yerevan Physics
Institute, Alikhanian Bros St. 2, Yerevan 375036, Armenia.
Publisher contact information for the Journal of Statistical Physics
is: Springer, 233 Spring St., New York, NY 10013, USA.
Science Letter
December 16, 2008
"Hidden Markov Processes (HMP) is one of the basic tools of the modern
probabilistic modeling. The characterization of their entropy remains
however an open problem," scientists in Yerevan, Armenia report
(see also Physics).
"Here the entropy of HMP is calculated via the cycle expansion of
the zeta-function, a method adopted from the theory of dynamical
systems. For a class of HMP this method produces exact results both for
the entropy and the moment-generating function. The latter allows to
estimate, via the Chernoff bound, the probabilities of large deviations
for the HMP," wrote A.E. Allahverdyan and colleagues.
The researchers concluded: "More generally, the method offers a
representation of the moment-generating function and of the entropy
via convergent series."
Allahverdyan and colleagues published their study in the Journal of
Statistical Physics (Entropy of Hidden Markov Processes via Cycle
Expansion. Journal of Statistical Physics, 2008;133(3):535-564).
For more information, contact A.E. Allahverdyan, Yerevan Physics
Institute, Alikhanian Bros St. 2, Yerevan 375036, Armenia.
Publisher contact information for the Journal of Statistical Physics
is: Springer, 233 Spring St., New York, NY 10013, USA.