An energy-based deep splitting method for the nonlinear filtering problem

DOI10.1007/S42985-023-00231-5MaRDI QIDQ6103776zbMATH OpenOpenAlexFDO

Authors Kasper Bågmark, Adam Andersson, Stig Larsson

Publication date 27 June 2023

Published in SN Partial Differential Equations and Applications (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2203.17153

zbMATH Keywords

deep learningenergy-based methodfiltering problemsplitting schemestochastic partial differential equationZakai equation

Mathematics Subject Classification ID

Signal detection and filtering (aspects of stochastic processes) (60G35) Bayesian inference (62F15) Density estimation (62G07) Inference from stochastic processes and prediction (62M20) Numerical solutions to stochastic differential and integral equations (65C30) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75) Artificial neural networks and deep learning (68T07)

Abstract: The purpose of this paper is to explore the use of deep learning for the solution of the nonlinear filtering problem. This is achieved by solving the Zakai equation by a deep splitting method, previously developed for approximate solution of (stochastic) partial differential equations. This is combined with an energy-based model for the approximation of functions by a deep neural network. This results in a computationally fast filter that takes observations as input and that does not require re-training when new observations are received. The method is tested on four examples, two linear in one and twenty dimensions and two nonlinear in one dimension. The method shows promising performance when benchmarked against the Kalman filter and the bootstrap particle filter.

Recommendations

• Deep filtering
• Splitting-up spectral method for nonlinear filtering problems with correlation noises
• An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations
• Approximation of the Zakaï Equation by the Splitting up Method
• A backward doubly stochastic differential equation approach for nonlinear filtering problems

Cites work

• An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations
• Bayesian filtering and smoothing
• Deep learning
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Deep splitting method for parabolic PDEs
• Equation of state calculations by fast computing machines
• Exact finite-dimensional filters for certain diffusions with nonlinear drift
• Fundamentals of stochastic filtering
• Handbook of Markov Chain Monte Carlo
• scientific article; zbMATH DE number 54145 (Why is no real title available?)
• scientific article; zbMATH DE number 3505981 (Why is no real title available?)
• scientific article; zbMATH DE number 1314977 (Why is no real title available?)
• scientific article; zbMATH DE number 2034520 (Why is no real title available?)
• scientific article; zbMATH DE number 3233089 (Why is no real title available?)
• Linear and non-linear filtering in mathematical finance: a review
• Mathematics of data fusion
• Monte Carlo sampling methods using Markov chains and their applications
• On Galerkin approximations for the Zakai equation with diffusive and point process observations
• On some filtering problems arising in mathematical finance
• On the Differential Equations Satisfied by Conditional Probablitity Densities of Markov Processes, with Applications
• On the optimal filtering of diffusion processes
• On the splitting-up method and stochastic partial differential equations
• Solving Fokker-Planck equation using deep learning
• Stochastic differential equations. An introduction with applications.

Cited in

(4)

• Deep filtering
• An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations
• Guided smoothing and control for diffusion processes
• Pathwise approximations to solving the filtering problem for the stochastic chemostat

This page was built for publication: An energy-based deep splitting method for the nonlinear filtering problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6103776)