Solving stochastic partial differential equations using neural networks in the Wiener chaos expansion

Ariel Neufeld, Philipp Schmocker
11/5/2024
stat.MLcs.LGmath.NA

No official code found. Best implementation: psc25/ChaosSPDE (2 stars, last commit 2024-11-08).

Abstract

In this paper, we solve stochastic partial differential equations (SPDEs) numerically by using (possibly random) neural networks in the truncated Wiener chaos expansion of their corresponding solution. Moreover, we provide some approximation rates for learning the solution of SPDEs with additive and/or multiplicative noise. Finally, we apply our results in numerical examples to approximate the solution of three SPDEs: the stochastic heat equation, the Heath-Jarrow-Morton equation, and the Zakai equation.

View on arXivView PDF

Code Implementations(1)

psc25/ChaosSPDECommunity100%
21PythonSep 25, 20241 years ago

Similar Papers

Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations

91% match2026

Chaos into Order: Neural Framework for Expected Value Estimation of Stochastic Partial Differential Equations

87% match2025

Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs

85% match2024

Convergence proofs and strong error bounds for forward-backward stochastic differential equations using neural network simulations

83% match2024

Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators

83% match1 repo2024

DeepSPoC: A Deep Learning-Based PDE Solver Governed by Sequential Propagation of Chaos

82% match2024

Cite this paper

@article{neufeld2024solving,
  title  = {Solving stochastic partial differential equations using neural networks in the Wiener chaos expansion},
  author = {Ariel Neufeld and Philipp Schmocker},
  year   = {2024},
  eprint = {2411.03384},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.03384v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.03384.svg)](https://codeofpaper.com/paper/2411.03384)

Discussion