A deep BSDE neural network method approximates unnormalized filtering densities for nonlinear Bayesian filtering, trained offline and applied online, with a hybrid a priori-a posteriori error bound proved under the parabolic Hörmander condition.
A convergent scheme for the Bayesian filtering problem based on the Fokker--Planck equation and deep splitting
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
A numerical scheme for approximating the nonlinear filtering density is introduced and its convergence rate is established, theoretically under a parabolic H\"{o}rmander condition, and empirically in numerical examples. In a prediction step, between the noisy and partial measurements at discrete times, the scheme approximates the Fokker--Planck equation with a deep splitting scheme, followed by an exact update through Bayes' formula. This results in a classical prediction-update filtering algorithm that operates online for new observation sequences post-training. The algorithm employs a sampling-based Feynman--Kac approach, designed to mitigate the curse of dimensionality. As a corollary we obtain the convergence rate for the approximation of the Fokker--Planck equation alone, disconnected from the filtering problem. The convergence analysis is complemented by a nonlinear $10$-dimensional numerical example demonstrating the robustness of the method.
fields
math.NA 2years
2025 2representative citing papers
The logarithmic deep backward SDE filter succeeds in a 100-dimensional Lorenz-96 model where particle and ensemble Kalman filters fail, while cutting inference time by two to five orders of magnitude.
citing papers explorer
-
Nonlinear filtering based on density approximation and deep BSDE prediction
A deep BSDE neural network method approximates unnormalized filtering densities for nonlinear Bayesian filtering, trained offline and applied online, with a hybrid a priori-a posteriori error bound proved under the parabolic Hörmander condition.
-
High-dimensional Bayesian filtering through deep density approximation
The logarithmic deep backward SDE filter succeeds in a 100-dimensional Lorenz-96 model where particle and ensemble Kalman filters fail, while cutting inference time by two to five orders of magnitude.