A deep solver for backward stochastic Volterra integral equations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Andersson, Kristoffer, Gnoatto, Alessandro, Trillos, Camilo Andrés García
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915562564616192
author Andersson, Kristoffer
Gnoatto, Alessandro
Trillos, Camilo Andrés García
author_facet Andersson, Kristoffer
Gnoatto, Alessandro
Trillos, Camilo Andrés García
contents We present the first deep-learning solver for backward stochastic Volterra integral equations (BSVIEs) and their fully-coupled forward-backward variants. The method trains a neural network to approximate the two solution fields in a single stage, avoiding the use of nested time-stepping cycles that limit classical algorithms. For the decoupled case we prove a non-asymptotic error bound composed of an a posteriori residual plus the familiar square root dependence on the time step. Numerical experiments are consistent with this rate and reveal two key properties: \emph{scalability}, in the sense that accuracy remains stable from low dimension up to 500 spatial variables while GPU batching keeps wall-clock time nearly constant; and \emph{generality}, since the same method handles coupled systems whose forward dynamics depend on the backward solution. These results open practical access to a family of high-dimensional, time-inconsistent problems in stochastic control and quantitative finance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A deep solver for backward stochastic Volterra integral equations
Andersson, Kristoffer
Gnoatto, Alessandro
Trillos, Camilo Andrés García
Numerical Analysis
Machine Learning
Probability
Mathematical Finance
65C30, 60H20, 60H35, 68T07
G.1.9; G.3; I.2.6; F.2.1
We present the first deep-learning solver for backward stochastic Volterra integral equations (BSVIEs) and their fully-coupled forward-backward variants. The method trains a neural network to approximate the two solution fields in a single stage, avoiding the use of nested time-stepping cycles that limit classical algorithms. For the decoupled case we prove a non-asymptotic error bound composed of an a posteriori residual plus the familiar square root dependence on the time step. Numerical experiments are consistent with this rate and reveal two key properties: \emph{scalability}, in the sense that accuracy remains stable from low dimension up to 500 spatial variables while GPU batching keeps wall-clock time nearly constant; and \emph{generality}, since the same method handles coupled systems whose forward dynamics depend on the backward solution. These results open practical access to a family of high-dimensional, time-inconsistent problems in stochastic control and quantitative finance.
title A deep solver for backward stochastic Volterra integral equations
topic Numerical Analysis
Machine Learning
Probability
Mathematical Finance
65C30, 60H20, 60H35, 68T07
G.1.9; G.3; I.2.6; F.2.1
url https://arxiv.org/abs/2505.18297