One model to solve them all: 2BSDE families via neural operators

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Furuya, Takashi, Kratsios, Anastasis, Possamaï, Dylan, Raonić, Bogdan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911246925692928
author Furuya, Takashi
Kratsios, Anastasis
Possamaï, Dylan
Raonić, Bogdan
author_facet Furuya, Takashi
Kratsios, Anastasis
Possamaï, Dylan
Raonić, Bogdan
contents We introduce a mild generative variant of the classical neural operator model, which leverages Kolmogorov--Arnold networks to solve infinite families of second-order backward stochastic differential equations ($2$BSDEs) on regular bounded Euclidean domains with random terminal time. Our first main result shows that the solution operator associated with a broad range of $2$BSDE families is approximable by appropriate neural operator models. We then identify a structured subclass of (infinite) families of $2$BSDEs whose neural operator approximation requires only a polynomial number of parameters in the reciprocal approximation rate, as opposed to the exponential requirement in general worst-case neural operator guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One model to solve them all: 2BSDE families via neural operators
Furuya, Takashi
Kratsios, Anastasis
Possamaï, Dylan
Raonić, Bogdan
Machine Learning
Numerical Analysis
Analysis of PDEs
Probability
Computational Finance
We introduce a mild generative variant of the classical neural operator model, which leverages Kolmogorov--Arnold networks to solve infinite families of second-order backward stochastic differential equations ($2$BSDEs) on regular bounded Euclidean domains with random terminal time. Our first main result shows that the solution operator associated with a broad range of $2$BSDE families is approximable by appropriate neural operator models. We then identify a structured subclass of (infinite) families of $2$BSDEs whose neural operator approximation requires only a polynomial number of parameters in the reciprocal approximation rate, as opposed to the exponential requirement in general worst-case neural operator guarantees.
title One model to solve them all: 2BSDE families via neural operators
topic Machine Learning
Numerical Analysis
Analysis of PDEs
Probability
Computational Finance
url https://arxiv.org/abs/2511.01125