Saved in:
Bibliographic Details
Main Authors: Xiao, Jichang, Wang, Xiaoqun
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.12582
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917702331793408
author Xiao, Jichang
Wang, Xiaoqun
author_facet Xiao, Jichang
Wang, Xiaoqun
contents Deep learning algorithms have been successfully applied to numerically solve linear Kolmogorov partial differential equations~(PDEs). A recent research shows that if the initial functions are bounded, the empirical risk minimization (ERM) over clipped ReLU networks generalizes well for solving the linear Kolmogorov PDE. In this paper, we propose to use a truncation technique to extend the generalization results for polynomially growing initial functions. Specifically, we prove that under an assumption, the sample size required to achieve an generalization error within $\varepsilon$ with a confidence level $\varrho$ grows polynomially in the size of the clipped neural networks and $(\varepsilon^{-1},\varrho^{-1})$, which means that the curse of dimensionality is broken. Moreover, we verify that the required assumptions hold for Black-Scholes PDEs and heat equations which are two important cases of linear Kolmogorov PDEs. For the approximation error, under certain assumptions, we establish approximation results for clipped ReLU neural networks when approximating the solution of Kolmogorov PDEs. Consequently, we establish that the ERM over artificial neural networks indeed overcomes the curse of dimensionality for a larger class of linear Kolmogorov PDEs.
format Preprint
id arxiv_https___arxiv_org_abs_2310_12582
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Error analysis for empirical risk minimization over clipped ReLU networks in solving linear Kolmogorov partial differential equations
Xiao, Jichang
Wang, Xiaoqun
Numerical Analysis
60H30, 65C30, 62M45, 68T07
Deep learning algorithms have been successfully applied to numerically solve linear Kolmogorov partial differential equations~(PDEs). A recent research shows that if the initial functions are bounded, the empirical risk minimization (ERM) over clipped ReLU networks generalizes well for solving the linear Kolmogorov PDE. In this paper, we propose to use a truncation technique to extend the generalization results for polynomially growing initial functions. Specifically, we prove that under an assumption, the sample size required to achieve an generalization error within $\varepsilon$ with a confidence level $\varrho$ grows polynomially in the size of the clipped neural networks and $(\varepsilon^{-1},\varrho^{-1})$, which means that the curse of dimensionality is broken. Moreover, we verify that the required assumptions hold for Black-Scholes PDEs and heat equations which are two important cases of linear Kolmogorov PDEs. For the approximation error, under certain assumptions, we establish approximation results for clipped ReLU neural networks when approximating the solution of Kolmogorov PDEs. Consequently, we establish that the ERM over artificial neural networks indeed overcomes the curse of dimensionality for a larger class of linear Kolmogorov PDEs.
title Error analysis for empirical risk minimization over clipped ReLU networks in solving linear Kolmogorov partial differential equations
topic Numerical Analysis
60H30, 65C30, 62M45, 68T07
url https://arxiv.org/abs/2310.12582