Global universal approximation with Brownian signatures

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ceylan, Mihriban, Prömel, David J.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909968724131840
author Ceylan, Mihriban
Prömel, David J.
author_facet Ceylan, Mihriban
Prömel, David J.
contents We establish $L^p$-type universal approximation theorems for general and non-anticipative functionals on suitable rough path spaces, showing that linear functionals acting on signatures of time-extended rough paths are dense with respect to an $L^p$-distance. To that end, we derive global universal approximation theorems for weighted rough path spaces. We demonstrate that these $L^p$-type universal approximation theorems apply in particular to Brownian motion. As a consequence, linear functionals on the signature of the time-extended Brownian motion can approximate any $p$-integrable stochastic process adapted to the Brownian filtration, including solutions to stochastic differential equations.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Global universal approximation with Brownian signatures
Ceylan, Mihriban
Prömel, David J.
Probability
Machine Learning
Mathematical Finance
We establish $L^p$-type universal approximation theorems for general and non-anticipative functionals on suitable rough path spaces, showing that linear functionals acting on signatures of time-extended rough paths are dense with respect to an $L^p$-distance. To that end, we derive global universal approximation theorems for weighted rough path spaces. We demonstrate that these $L^p$-type universal approximation theorems apply in particular to Brownian motion. As a consequence, linear functionals on the signature of the time-extended Brownian motion can approximate any $p$-integrable stochastic process adapted to the Brownian filtration, including solutions to stochastic differential equations.
title Global universal approximation with Brownian signatures
topic Probability
Machine Learning
Mathematical Finance
url https://arxiv.org/abs/2512.16396