Sufficient conditions for finite dimensionality of filters in discrete time: a Laplace transform-based approach
Runggaldier, Wolfgang J. ; Spizzichino, Fabio
Bernoulli, Tome 7 (2001) no. 6, p. 211-221 / Harvested from Project Euclid
The discrete-time filtering problem can be seen as a dynamic generalization of the classical Bayesian inference problem. For practical applications it is important to identify filtering models that, analogously to the linear Gaussian model (Kalman filter), admit a finite-dimensional filter or, equivalently, a finite-dimensional family of filter-conjugate distributions. Our main purpose here is to give sufficient conditions for the existence of finite-dimensional filters. We use a method, based on the Laplace transform, which is also constructive.
Publié le : 2001-04-14
Classification:  dynamic Bayes formula,  exponential families,  finite-dimensional filters,  infinitely divisible distributions,  inverse Laplace transform,  state-space models
@article{1080222084,
     author = {Runggaldier, Wolfgang J. and Spizzichino, Fabio},
     title = {Sufficient conditions for finite dimensionality of filters in discrete time: a Laplace transform-based approach},
     journal = {Bernoulli},
     volume = {7},
     number = {6},
     year = {2001},
     pages = { 211-221},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1080222084}
}
Runggaldier, Wolfgang J.; Spizzichino, Fabio. Sufficient conditions for finite dimensionality of filters in discrete time: a Laplace transform-based approach. Bernoulli, Tome 7 (2001) no. 6, pp.  211-221. http://gdmltest.u-ga.fr/item/1080222084/