Discussion Papers 2021

CIRJE-F-1178

"Deep Asymptotic Expansion: Application to Financial Mathematics"

Author Name

Iguchi, Yuga, Riu Naito, Yusuke Okano, Akihiko Takahashi and Toshihiro Yamada

Date

November 2021

Full Paper PDF file
Remarks

Revised in February 2022.

Published in Proceedings of IEEE CSDE 2021.

Abstract

The paper proposes a new computational scheme for diffusion semigroups based on an asymptotic expansion with weak approximation and deep learning algorithm to solve high-dimensional Kolmogorov partial differential equations (PDEs). In particular, we give a spatial approximation for the solution of d-dimensional PDEs on a range [a, b] d without suffering from the curse of dimensionality.

Keywords: Deep learning, Asymptotic expansion, Weak approximation, Kolmogorov PDEs, Malliavin calculus, Curse of dimensionality