Recursive Nonlinear Estimation of Non-linear/Non-Gaussian Dynamic Models

While the general theory of recursive Bayesian estimation of dynamic models is well developed, its practical implementation is restricted to a narrow class of models, typically models with linear dynamics and Gaussian stochastics. The theoretically optimal solution is infeasible for non-linear and/or non-Gaussian models due to its excessive demands on computational memory and time. Parameter estimation of such models requires approximation of the theoretical solution. The paper describes one possible framework for such approximation that is based on measuring of Kullback-Leibler distance between the empirical and theoretical distributions of observed data.