A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations

09/28/2022
by   Jiang Yu Nguwi, et al.
0

Recent work on Path-Dependent Partial Differential Equations (PPDEs) has shown that PPDE solutions can be approximated by a probabilistic representation, implemented in the literature by the estimation of conditional expectations using regression. However, a limitation of this approach is to require the selection of a basis in a function space. In this paper, we overcome this limitation by the use of deep learning methods, and we show that this setting allows for the derivation of error bounds on the approximation of conditional expectations. Numerical examples based on a two-person zero-sum game, as well as on Asian and barrier option pricing, are presented. In comparison with other deep learning approaches, our algorithm appears to be more accurate, especially in large dimensions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/04/2020

PDGM: a Neural Network Approach to Solve Path-Dependent Partial Differential Equations

In this paper we propose a generalization of the Deep Galerking Method (...
research
03/07/2022

A deep branching solver for fully nonlinear partial differential equations

We present a multidimensional deep learning implementation of a stochast...
research
06/03/2022

Convergence Analysis of the Deep Splitting Scheme: the Case of Partial Integro-Differential Equations and the associated FBSDEs with Jumps

High-dimensional parabolic partial integro-differential equations (PIDEs...
research
08/22/2019

`Regression Anytime' with Brute-Force SVD Truncation

We propose a new least-squares Monte Carlo algorithm for the approximati...
research
04/27/2023

A framework for rigorous computational methods using Haar wavelets for differential equations

This work presents a framework for a-posteriori error-estimating algorit...
research
08/24/2021

Deep Signature FBSDE Algorithm

We propose a deep signature/log-signature FBSDE algorithm to solve forwa...
research
06/02/2021

Numerical valuation of American basket options via partial differential complementarity problems

We study the principal component analysis based approach introduced by R...

Please sign up or login with your details

Forgot password? Click here to reset