Finite-dimensionality in discrete-time nonlinear filtering from a bayesian statistics viewpoint
Discrete-time filtering problems can be considered as sequential Bayesian estimation problems.
The purpose of the present study is to explore the relationships between standard Bayesian Statistics and discrete time Filtering with the aim of a better understanding of the problem of the existence of finite dimensional filters.
Unable to display preview. Download preview PDF.
- O. Barndorff-Nielsen and K. Pedersen "Sufficient Data Reduction and Exponential Families". Mathematica Scandinavica 22, 197–202 (1968).Google Scholar
- J.A. Bather "Invariant Conditional Distributions" Ann. Math. Stat. 36, 829–846 (1965).Google Scholar
- G. Di Masi, W.J. Runnggaldier — International Conference on "Stochastic Optimization", Kiev, Sept. 1984.Google Scholar
- G. Di Masi, W.J. Runggaldier. "Approximations and bounds for discrete-time non linear filtering" in A. Bensoussan, J.L. Lions (eds.) "Analysis and Optimization of Systems" L.N. in Control and Information Sciences 44, 191–202, Springer-Verlag (1982).Google Scholar
- S.N. Ethier, T.G. Kurtz "Markov Processes: characterization and convergence" (Wiley, to appear).Google Scholar
- H. Korezlioglu "Computational problems in non linear filtering". In this volume.Google Scholar
- J. Levine "A class of non linear systems in discrete-time and continuous-time admitting a finite-dimensional filter". In this volume.Google Scholar
- G. Sawitski "Exact filtering in exponential families: discrete time" in M. Kohlmann, W. Vogel (eds.) Stochastic control theory and stochastic differential systems, J.N. in Control and Informations Sciences 16, 554–558 (1979).Google Scholar
- G. Sawitzki "Finite Dimensional Filter Systems in Discrete Time". Stochastic, 5, 107–114 (1981).Google Scholar
- J.H. Van Schuppen, "Stochastic filtering theory: a discussion on concepts, methods, and results", in M. Kohlmann, W. Vogel (eds.), Lecture notes in Control and Information Sciences 16, Springer-Verlag (1979).Google Scholar