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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dehshiri, Mahdi, Martinez, Kerlyns, Viitasaari, Lauri
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910192683188224
author Dehshiri, Mahdi
Martinez, Kerlyns
Viitasaari, Lauri
author_facet Dehshiri, Mahdi
Martinez, Kerlyns
Viitasaari, Lauri
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04168
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Error analysis for learning fractional stochastic differential equations with applications in neural approximations
Dehshiri, Mahdi
Martinez, Kerlyns
Viitasaari, Lauri
Probability
Numerical Analysis
60H10, 65C30, 68T07, 68T05, 65L20, 62G05
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.
title Error analysis for learning fractional stochastic differential equations with applications in neural approximations
topic Probability
Numerical Analysis
60H10, 65C30, 68T07, 68T05, 65L20, 62G05
url https://arxiv.org/abs/2605.04168