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

by   Rüdiger Frey, et al.

High-dimensional parabolic partial integro-differential equations (PIDEs) appear in many applications in insurance and finance. Existing numerical methods suffer from the curse of dimensionality or provide solutions only for a given space-time point. This gave rise to a growing literature on deep learning based methods for solving partial differential equations; results for integro-differential equations on the other hand are scarce. In this paper we consider an extension of the deep splitting scheme due to Beck, Becker, Cheridito, Jentzen, Neufeld (2021) and Germain, Pham, Warin (2022) to PIDEs. Our main contribution is a convergence analysis of the scheme. Moreover we discuss several test case studies to show the viability of our approach.


page 1

page 2

page 3

page 4


Deep Neural Network Algorithms for Parabolic PIDEs and Applications in Insurance Mathematics

In recent years a large literature on deep learning based methods for th...

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

Classical numerical methods for solving partial differential equations s...

Exact splitting methods for kinetic and Schrödinger equations

In [8], some exact splittings are proposed for inhomogeneous quadratic d...

A Root-Free Splitting-Lemma for Systems of Linear Differential Equations

We consider the formal reduction of a system of linear differential equa...

Dimensionally Consistent Preconditioning for Saddle-Point Problems

The preconditioned iterative solution of large-scale saddle-point system...

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

Recent work on Path-Dependent Partial Differential Equations (PPDEs) has...