Asymptotic stability of beneš filters
作者:
D.L. Ocone,
期刊:
Stochastic Analysis and Applications
(Taylor Available online 1999)
卷期:
Volume 17,
issue 6
页码: 1053-1074
ISSN:0736-2994
年代: 1999
DOI:10.1080/07362999908809648
出版商: Marcel Dekker, Inc.
数据来源: Taylor
摘要:
The asymptotic behavior of the explicit solution to the Beneš filtering problem is studied. It is shown that there is a universal, data-dependent change of location that renders any Beneš filter asymptotic to a fixed normal distribution. Asymptotic stability of Beneš filters follows as a result; that is, the variational distance between any two, differently initialized solutions of the Kushner-Stratonovich equation converges to zero in the infinite time limit. It is also shown the relative entropy between differently initialized solutions converges to zero. More careful relative entropy bounds are used to derive exponential convergence of the variational distance between filters
点击下载:
PDF (589KB)
返 回