Solving the Kolmogorov PDE by means of deep learning

DOI10.1007/s10915-021-01590-0zbMath1490.65006arXiv1806.00421OpenAlexW3191818024WikidataQ114225594 ScholiaQ114225594MaRDI QIDQ2051092

Arnulf Jentzen, Sebastian Becker, Christian Beck, Nor Jaafari, Philipp Grohs

Publication date: 1 September 2021

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.00421

zbMATH Keywords

stochastic differential equationsKolmogorov equationsdeep learningnumerical approximation method

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) PDEs with randomness, stochastic partial differential equations (35R60) Numerical solutions to stochastic differential and integral equations (65C30) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (38)

Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations ⋮ Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space ⋮ Convergence of a Robust Deep FBSDE Method for Stochastic Control ⋮ A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations ⋮ Probability measure-valued polynomial diffusions ⋮ Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms ⋮ Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities ⋮ Approximations with deep neural networks in Sobolev time-space ⋮ A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions ⋮ Full error analysis for the training of deep neural networks ⋮ Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data ⋮ An unsupervised deep learning approach to solving partial integro-differential equations ⋮ Unbiased Deep Solvers for Linear Parametric PDEs ⋮ Numerical computation of probabilities for nonlinear SDEs in high dimension using Kolmogorov equation ⋮ DEEP EQUILIBRIUM NETS ⋮ Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes ⋮ Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning ⋮ Space-time error estimates for deep neural network approximations for differential equations ⋮ Probability computation for high-dimensional semilinear SDEs driven by isotropic \(\alpha\)-stable processes via mild Kolmogorov equations ⋮ Improved Analysis of PINNs: Alleviate the CoD for Compositional Solutions ⋮ Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations ⋮ Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus ⋮ Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing ⋮ Pricing options on flow forwards by neural networks in a Hilbert space ⋮ A space-time adaptive low-rank method for high-dimensional parabolic partial differential equations ⋮ Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions ⋮ Control of partial differential equations via physics-informed neural networks ⋮ Approximation properties of residual neural networks for Kolmogorov PDEs ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations ⋮ Deep Splitting Method for Parabolic PDEs ⋮ Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations ⋮ Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation ⋮ An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations ⋮ Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks ⋮ Approximative Policy Iteration for Exit Time Feedback Control Problems Driven by Stochastic Differential Equations using Tensor Train Format ⋮ DNN expression rate analysis of high-dimensional PDEs: application to option pricing ⋮ Approximation spaces of deep neural networks

Uses Software

• Adam
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Euler approximations with varying coefficients: the case of superlinearly growing diffusion coefficients
• Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• A note on tamed Euler approximations
• Finite difference methods for the weak solutions of the Kolmogorov equation for the density of both diffusion and conditional diffusion processes
• Numerical solution of SDE through computer experiments. Including floppy disk
• Strong convergence rates for Cox-Ingersoll-Ross processes -- full parameter range
• Strong convergence of full-discrete nonlinearity-truncated accelerated exponential Euler-type approximations for stochastic Kuramoto-Sivashinsky equations
• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• A distribution-free theory of nonparametric regression
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• Lower error bounds for the stochastic gradient descent optimization algorithm: sharp convergence rates for slowly and fast decaying learning rates
• Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
• Loss of regularity for Kolmogorov equations
• Compact finite difference method for American option pricing
• Stochastic simulation and Monte Carlo methods. Mathematical foundations of stochastic simulation
• Hypoelliptic second order differential equations
• Continuous Markov processes and stochastic equations
• On the mathematical foundations of learning
• Numerical approximations of stochastic differential equations with non-globally Lipschitz continuous coefficients
• On the discretization schemes for the CIR (and Bessel squared) processes
• Multilevel Monte Carlo Path Simulation
• Minimal Errors for Strong and Weak Approximation of Stochastic Differential Equations
• Exponential integrability properties of numerical approximation processes for nonlinear stochastic differential equations
• Solving high-dimensional partial differential equations using deep learning
• Deep Neural Network Approximation Theory
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations
• Deep optimal stopping
• Understanding Machine Learning
• Numerical Integration of Stochastic Differential Equations with Nonglobally Lipschitz Coefficients
• Probability theory. A comprehensive course
• Stochastic differential equations. An introduction with applications.

This page was built for publication: Solving the Kolmogorov PDE by means of deep learning