Universal approximation property of neural stochastic differential equations

Anna P. Kwossek, David J. Prömel, Josef Teichmann
3/20/2025
math.PRcs.LGmath.FA

No confident code implementation found for this paper.

Abstract

We identify various classes of neural networks that are able to approximate continuous functions locally uniformly subject to fixed global linear growth constraints. For such neural networks the associated neural stochastic differential equations can approximate general stochastic differential equations, both of Itô diffusion type, arbitrarily well. Moreover, quantitative error estimates are derived for stochastic differential equations with sufficiently regular coefficients.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Approximation properties of neural ODEs

85% match2025

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

84% match2024

Generalization bounds for neural ordinary differential equations and deep residual networks

84% match2023

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

83% match1 repo812024

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

83% match1 repo812026

A Constructive Approach to Function Realization by Neural Stochastic Differential Equations

82% match2023

Cite this paper

@article{kwossek2025universal,
  title  = {Universal approximation property of neural stochastic differential equations},
  author = {Anna P. Kwossek and David J. Prömel and Josef Teichmann},
  year   = {2025},
  eprint = {2503.16696},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.16696v1}
}

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/2503.16696.svg)](https://codeofpaper.com/paper/2503.16696)

Discussion