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={Martin Hutzenthaler and Arnulf Jentzen and Thomas Kruse and Tuan Anh Nguyen},
  journal={arXiv: Numerical Analysis},
  year={2019}
}
  • Martin Hutzenthaler, Arnulf Jentzen, +1 author Tuan Anh Nguyen
  • Published 2019
  • Computer Science, Mathematics
  • arXiv: Numerical Analysis
  • 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… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 35 CITATIONS

    Deep neural network approximations for Monte Carlo algorithms

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 1 Highly Influenced Citations

    • Averaged 12 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES