A Robustification Approach to Stability and to Uniform Particle Approximation of Nonlinear Filters : the Example of Pseudo--Mixing Signals - Inria - Institut national de recherche en sciences et technologies du numérique
Reports (Research Report) Year : 2002

A Robustification Approach to Stability and to Uniform Particle Approximation of Nonlinear Filters : the Example of Pseudo--Mixing Signals

François Le Gland
  • Function : Author
  • PersonId : 832228
Nadia Oudjane
  • Function : Author

Abstract

We propose a new approach to study the stability of the optimal filter w.r.t. its initial condition, by introducing a «robust» filter, which is exponentially stable and which approximates the optimal filter uniformly in time. The «robust» filter is obtained here by truncation of the likelihood function, and the robustification result is proved under the assumption that the Markov transition kernel satisfies a pseudo--mixing condition (weaker than the usual mixing condition), and that the observations are «sufficiently good». This robustification approach allows us to prove also the uniform convergence of several particle approximations to the optimal filter, in some cases of nonergodic signals.
Fichier principal
Vignette du fichier
RR-4431.pdf (353.89 Ko) Télécharger le fichier

Dates and versions

inria-00072157 , version 1 (23-05-2006)

Identifiers

  • HAL Id : inria-00072157 , version 1

Cite

François Le Gland, Nadia Oudjane. A Robustification Approach to Stability and to Uniform Particle Approximation of Nonlinear Filters : the Example of Pseudo--Mixing Signals. [Research Report] RR-4431, INRIA. 2002. ⟨inria-00072157⟩
169 View
173 Download

Share

More