Deep learning based numerical approximation algorithms for stochastic partial differential equations
arXiv:2012.01194
Abstract
In this article, we introduce a deep learning based approximation algorithm for SPDEs. Our approach employs neural networks to approximate the solutions of SPDEs along given realizations of the driving noise process. If applied to a set of simulated noise trajectories, it yields empirical distributions of SPDE solutions, from which functionals like the mean and variance can be estimated. We test the performance of the method on stochastic heat equations with additive and multiplicative noise as well as stochastic Black-Scholes equations with multiplicative noise and Zakai equations from nonlinear filtering theory. In all cases, the proposed algorithm yields accurate results with short runtimes in up to 100 space dimensions.
References in corpus (13)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- DGM: A deep learning algorithm for solving partial differential equations
- Solving high-dimensional partial differential equations using deep learning
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
- Deep splitting method for parabolic PDEs
- Loss of regularity for Kolmogorov equations
- Higher order strong approximations of semilinear stochastic wave equation with additive space-time white noise
- On implicit and explicit discretization schemes for parabolic SPDEs in any dimension
- Noise regularization and computations for the 1-dimensional stochastic Allen-Cahn problem
- On nonlinear Feynman-Kac formulas for viscosity solutions of semilinear parabolic partial differential equations
- A modified semi--implict Euler-Maruyama Scheme for finite element discretization of SPDEs with additive noise