Parameter estimation in non-linear state-space models by automatic differentiation of non-linear Kalman filters

In this article, we propose automatic differentiation based methods for parameter estimation in non-linear state-space models. We use extended Kalman filter and cubature Kalman filters for approximating the negative log-likelihood (i.e., the energy function) of the parameter posterior distribution and compute the gradients and Hessians of this function by using automatic differentiation of the filter recursions. The proposed approach enables computing MAP estimates and forming Laplace approximations for the parameter posterior without a need for implementing complicated derivative recursions or manual computation of Jacobians. The methods are demonstrated in parameter estimation problems on a pendulum model and coordinated turn model.