Information geometric nonlinear filtering
From MaRDI portal
Signal detection and filtering (aspects of stochastic processes) (60G35) Continuous-time Markov processes on general state spaces (60J25) Diffusion processes (60J60) Bayesian inference (62F15) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31) Filtering in stochastic control theory (93E11) Measures of information, entropy (94A17)
Abstract: This paper develops information geometric representations for nonlinear filters in continuous time. The posterior distribution associated with an abstract nonlinear filtering problem is shown to satisfy a stochastic differential equation on a Hilbert information manifold. This supports the Fisher metric as a pseudo-Riemannian metric. Flows of Shannon information are shown to be connected with the quadratic variation of the process of posterior distributions in this metric. Apart from providing a suitable setting in which to study such information-theoretic properties, the Hilbert manifold has an appropriate topology from the point of view of multi-objective filter approximations. A general class of finite-dimensional exponential filters is shown to fit within this framework, and an intrinsic evolution equation, involving Amari's -covariant derivative, is developed for such filters. Three example systems, one of infinite dimension, are developed in detail.
Recommendations
Cites work
- A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
- A Variational Approach to Nonlinear Estimation
- An infinite-dimensional statistical manifold modelled on Hilbert space
- Approximate nonlinear filtering by projection on exponential manifolds of densities
- Connections on Non-Parametric Statistical Manifolds by Orlicz Space Geometry
- Dual Kalman–Bucy Filters and Interactive Entropy Production
- Dynamical equations for optimal nonlinear filtering
- Elements of Information Theory
- Estimation of Stochastic Systems: Arbitrary System Process with Additive White Noise Observation Errors
- Exponential statistical manifold
- scientific article; zbMATH DE number 5871504 (Why is no real title available?)
- Information and entropy flow in the Kalman-Bucy filter
- Interactive statistical mechanics and nonlinear filtering
- On the Calculation of Mutual Information
- Second order efficiency of minimum contrast estimators in a curved exponential family
- The exponential statistical manifold: mean parameters, orthogonality and space transformations
Cited in
(13)- Nonlinear filtering and Riemannian scalar curvature, \({\mathbb{R}}\)
- Rho-tau embedding and gauge freedom in information geometry
- A class of non-parametric statistical manifolds modelled on Sobolev space
- Nonlinear filtering and information geometry: a Hilbert manifold approach
- Geometry of Kalman filters
- scientific article; zbMATH DE number 3968477 (Why is no real title available?)
- Manifolds of differentiable densities
- scientific article; zbMATH DE number 7012760 (Why is no real title available?)
- Information geometry applications for optimizing numerical simulations
- Nonlinear modeling and processing using empirical intrinsic geometry with application to biomedical imaging
- Optimal projection filters with information geometry
- Global differentiable structures for the Fisher-Rao and Kantorovich-Wasserstein-Otto metrics
- A novel high speed transport protocol based on explicit virtual load feedback
This page was built for publication: Information geometric nonlinear filtering
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5500470)
