A convergent scheme for the Bayesian filtering problem based on the Fokker--Planck equation and deep splitting
Not on the map. Why?
Abstract (arXiv)
A numerical scheme for approximating the nonlinear filtering density is introduced and its convergence rate is established, theoretically under a parabolic H"ormander 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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 62 references that are in the map. First posted on arXiv 22 Sep 2024.
Builds on
18 of 62 references.
References · 18
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
- 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 581
- 2017Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equationscited by 188
- 2019Deep splitting method for parabolic PDEscited by 53
- 2022Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spacescited by 50
- 2018Solving the Kolmogorov PDE by means of deep learningcited by 41
- 2024Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck Equationscited by 22
- 2020Deep learning based numerical approximation algorithms for stochastic partial differential equationscited by 11
- 2022Convergence of a robust deep FBSDE method for stochastic controlcited by 11
- 2024Conditioning diffusion models by explicit forward-backward bridgingcited by 11
- 2016High-dimensional Filtering using Nested Sequential Monte Carlocited by 8
- 2022An energy-based deep splitting method for the nonlinear filtering problemcited by 7
6 more
- 2024Learning Optimal Filters Using Variational Inferencecited by 7
- 2020Automatic Backward Filtering Forward Guiding for Markov processes and graphical modelscited by 5
- 2022An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equationscited by 5
- 2022Deep Learning for the Benes Filtercited by 4
- 2019A High-Dimensional Particle Filter Algorithmcited by 2
- 2024Particle-MALA and Particle-mGRAD: Gradient-based MCMC methods for high-dimensional state-space modelscited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.