Uniform Observability of Hidden Markov Models and Filter Stability for Unstable Signals

@inproceedings{Handel2009UniformOO,
  title={Uniform Observability of Hidden Markov Models and Filter Stability for Unstable Signals},
  author={Ramon van Handel},
  year={2009}
}
A hidden Markov model is called observable if distinct initi al laws give rise to distinct laws of the observation process. Observabi lity implies stability of the nonlinear filter when the signal process is tight, but t his need not be the case when the signal process is unstable. This paper introdu ces a stronger notion of uniform observability which guarantees stability o f the nonlinear filter in the absence of stability assumptions on the signal. By dev eloping certain uniform… CONTINUE READING
8 Citations
33 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 33 references

On the consistency of Bayes estimates

  • P. DIACONIS, D. FREEDMAN
  • Ann. Statist
  • 1986
Highly Influential
3 Excerpts

Stability of the discrete time filter in terms of t he tails of noise distributions

  • D. CRISAN, K. HEINE
  • J . Lond . Math . Soc .
  • 2008
1 Excerpt

O

  • C. D. A LIPRANTIS, BURKINSHAW
  • 2006

On a role of predictor in the filtering stability

  • P. CHIGANSKY, R. L IPTSER
  • Electr. Commun. Probab
  • 2006
1 Excerpt

Stability and uniform particle approximation of nonlinear filters in case of non ergodic signals

  • N. OUDJANE, S. RUBENTHALER
  • Stoch. Anal. Appl
  • 2005
1 Excerpt

Stability of the filter equation for a time - dependent signal on R d

  • W. Stannat
  • Appl . Math . Optim .
  • 2005

Stability of the filter equation for a time-depen d t signal onR

  • W. STANNAT
  • Appl. Math. Optim
  • 2005

Similar Papers

Loading similar papers…