# A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations.

@article{Hutzenthaler2019APT, title={A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations.}, author={M. Hutzenthaler and A. Jentzen and T. Kruse and T. Nguyen}, journal={arXiv: Numerical Analysis}, year={2019} }

Deep neural networks and other deep learning methods have very successfully been applied to the numerical approximation of high-dimensional nonlinear parabolic partial differential equations (PDEs), which are widely used in finance, engineering, and natural sciences. In particular, simulations indicate that algorithms based on deep learning overcome the curse of dimensionality in the numerical approximation of solutions of semilinear PDEs. For certain linear PDEs this has also been proved… Expand

#### Topics from this paper

#### 66 Citations

Space-time deep neural network approximations for high-dimensional partial differential equations

- Computer Science, Mathematics
- ArXiv
- 2020

Some machine learning schemes for high-dimensional nonlinear PDEs

- Mathematics, Computer Science
- Math. Comput.
- 2020

Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems

- Mathematics, Computer Science
- ArXiv
- 2019

Deep neural network approximations for Monte Carlo algorithms

- Computer Science, Mathematics
- ArXiv
- 2019

Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities

- Mathematics, Computer Science
- ArXiv
- 2019

On the Representation of Solutions to Elliptic PDEs in Barron Spaces

- Computer Science, Mathematics
- ArXiv
- 2021

A Theoretical Analysis of Deep Neural Networks and Parametric PDEs

- Mathematics, Computer Science
- ArXiv
- 2019

#### References

SHOWING 1-10 OF 32 REFERENCES

A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients

- Mathematics, Computer Science
- ArXiv
- 2018

Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations

- Mathematics, Medicine
- Proceedings of the Royal Society A
- 2020

A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations

- Mathematics, Computer Science
- ArXiv
- 2018

Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities

- Mathematics, Computer Science
- ArXiv
- 2019

Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks.

- Mathematics
- 2019

Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations

- Mathematics, Computer Science
- ArXiv
- 2018

A deep learning solution approach for high-dimensional random differential equations

- Computer Science, Mathematics
- 2019

Solving stochastic differential equations and Kolmogorov equations by means of deep learning

- Mathematics, Computer Science
- ArXiv
- 2018

A Deep Neural Network Surrogate for High-Dimensional Random Partial Differential Equations

- Computer Science, Physics
- ArXiv
- 2018