error
Die ETH-Bibliothek ist vom Mi., 24.12.2025 bis So., 04.01.2026 geschlossen. Während dieser Zeit können weiterhin neue Einträge in der Research Collection eingereicht werden. Ab Mo., 05.01.2026 sind wir gerne wieder für Sie da. // The ETH Library will be closed from Wednesday, December 24, 2025, to Sunday, January 4, 2026. During this time, new publications can still be submitted to the Research Collection. We will be happy to assist you again starting Monday, January 5, 2026.
 

Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations


METADATA ONLY
Loading...

Date

2018-09

Publication Type

Report

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined Deep Learning, revolutionized the area of artificial intelligence, machine learning, and data analysis. More recently, these methods have been applied to the numerical solution of high dimensional partial differential equations (PDEs) with great success. In particular, recent simulations indicate that deep learning based algorithms are capable of overcoming the curse of dimensionality for the numerical solution of linear Kolmogorov PDEs. Kolmogorov PDEs have been widely used in models from engineering, finance, and the natural sciences. In particular Kolmogorov PDEs are highly employed in models for the approximative pricing of financial derivatives. Nearly all approximation methods for Kolmogorov PDEs in the literature suffer under the curse of dimensionality. By contrast, in recent work by some of the authors it was shown that deep ReLU neural networks are capable of approximating solutions of Kolmogorov PDEs without incurring the curse of dimensionality. The present paper considerably strengthens these results by providing an analysis of the generalization error. In particular we show that for Kolmogorov PDEs with affine drift and diffusion coefficients and a given accuracy ε>0, ERM over deep neural network hypothesis classes of size scaling polynomially in the dimension d and ε−1 and with a number of training samples scaling polynomially in the dimension d and ε−1 approximates the solution of the Kolmogorov PDE to within accuracy ε with high probability. We conclude that ERM over deep neural network hypothesis classes breaks the curse of dimensionality for the numerical solution of linear Kolmogorov PDEs with affine drift and diffusion coefficients. To the best of our knowledge this is the first rigorous mathematical result that proves the efficiency of deep learning methods for high dimensional problems.

Publication status

published

Editor

Book title

Journal / series

SAM Research Report

Volume

2018-31

Pages / Article No.

Publisher

Seminar for Applied Mathematics, ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03951 - Jentzen, Arnulf (ehemalig) / Jentzen, Arnulf (former) check_circle

Notes

Funding

Related publications and datasets