Deep Learning Based on Randomized Quasi-Monte Carlo Method for Solving Linear Kolmogorov Partial Differential Equation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xiao, Jichang, Fu, Fengjiang, Wang, Xiaoqun
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911930148454400
author Xiao, Jichang
Fu, Fengjiang
Wang, Xiaoqun
author_facet Xiao, Jichang
Fu, Fengjiang
Wang, Xiaoqun
contents Deep learning algorithms have been widely used to solve linear Kolmogorov partial differential equations~(PDEs) in high dimensions, where the loss function is defined as a mathematical expectation. We propose to use the randomized quasi-Monte Carlo (RQMC) method instead of the Monte Carlo (MC) method for computing the loss function. In theory, we decompose the error from empirical risk minimization~(ERM) into the generalization error and the approximation error. Notably, the approximation error is independent of the sampling methods. We prove that the convergence order of the mean generalization error for the RQMC method is $O(n^{-1+ε})$ for arbitrarily small $ε>0$, while for the MC method it is $O(n^{-1/2+ε})$ for arbitrarily small $ε>0$. Consequently, we find that the overall error for the RQMC method is asymptotically smaller than that for the MC method as $n$ increases. Our numerical experiments show that the algorithm based on the RQMC method consistently achieves smaller relative $L^{2}$ error than that based on the MC method.
format Preprint
id arxiv_https___arxiv_org_abs_2310_18100
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep Learning Based on Randomized Quasi-Monte Carlo Method for Solving Linear Kolmogorov Partial Differential Equation
Xiao, Jichang
Fu, Fengjiang
Wang, Xiaoqun
Numerical Analysis
65C30, 65D30, 65N15, 68T07
Deep learning algorithms have been widely used to solve linear Kolmogorov partial differential equations~(PDEs) in high dimensions, where the loss function is defined as a mathematical expectation. We propose to use the randomized quasi-Monte Carlo (RQMC) method instead of the Monte Carlo (MC) method for computing the loss function. In theory, we decompose the error from empirical risk minimization~(ERM) into the generalization error and the approximation error. Notably, the approximation error is independent of the sampling methods. We prove that the convergence order of the mean generalization error for the RQMC method is $O(n^{-1+ε})$ for arbitrarily small $ε>0$, while for the MC method it is $O(n^{-1/2+ε})$ for arbitrarily small $ε>0$. Consequently, we find that the overall error for the RQMC method is asymptotically smaller than that for the MC method as $n$ increases. Our numerical experiments show that the algorithm based on the RQMC method consistently achieves smaller relative $L^{2}$ error than that based on the MC method.
title Deep Learning Based on Randomized Quasi-Monte Carlo Method for Solving Linear Kolmogorov Partial Differential Equation
topic Numerical Analysis
65C30, 65D30, 65N15, 68T07
url https://arxiv.org/abs/2310.18100