English

Error analysis for learning fractional stochastic differential equations with applications in neural approximations

Probability 2026-05-07 v1 Numerical Analysis Numerical Analysis

Abstract

This paper develops a framework for the error analysis in nonparametric model fitting of fractional stochastic differential equations based on discrete observations. We identify and quantify the main error sources -- time discretization, coefficient approximation, and model fitting error -- within a unified framework. Through Sobolev-type norms, we derive convergence rates that incorporate the regularity of trajectories, thereby capturing the interaction of these error components. To demonstrate the applicability of the theory, we introduce a training scheme for coefficient function estimation based on shallow neural networks and a recurrent architecture. Numerical experiments validate the theoretical findings and illustrate the effectiveness of the approach.

Keywords

Cite

@article{arxiv.2605.04168,
  title  = {Error analysis for learning fractional stochastic differential equations with applications in neural approximations},
  author = {Mahdi Dehshiri and Kerlyns Martinez and Lauri Viitasaari},
  journal= {arXiv preprint arXiv:2605.04168},
  year   = {2026}
}
R2 v1 2026-07-01T12:51:37.862Z