An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations

DOI10.1007/s40072-022-00260-yzbMath1504.65004arXiv2201.03283OpenAlexW4221139972WikidataQ114219503 ScholiaQ114219503MaRDI QIDQ2093308

Salvador Ortiz-Latorre, Alexander Lobbe, Dan Crisan

Publication date: 7 November 2022

Published in: Stochastic and Partial Differential Equations. Analysis and Computations (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.03283

zbMATH Keywords

stochastic filteringdeep learningnumerical approximation of stochastic PDEs

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Filtering in stochastic control theory (93E11) Monte Carlo methods (65C05) Numerical solutions to stochastic differential and integral equations (65C30)

Related Items (1)

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

Uses Software

• TensorFlow
• AdaGrad
• Adam
• DGM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Fundamentals of stochastic filtering
• On some filtering problems arising in mathematical finance
• On the splitting-up method and stochastic partial differential equations
• Inferring solutions of differential equations using noisy multi-fidelity data
• DGM: a deep learning algorithm for solving partial differential equations
• Neural networks-based backward scheme for fully nonlinear PDEs
• Solving the Kolmogorov PDE by means of deep learning
• Extensions of the deep Galerkin method
• Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications
• Linear and non-linear filtering in mathematical finance: a review
• Deep Splitting Method for Parabolic PDEs
• Deep backward schemes for high-dimensional nonlinear PDEs
• Solving high-dimensional partial differential equations using deep learning
• Learning representations by back-propagating errors
• Advanced Lectures on Machine Learning
• An Accelerated Splitting-up Method for Parabolic Equations
• Particle Filtering for Stochastic Navier--Stokes Signal Observed with Linear Additive Noise

This page was built for publication: An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations