Solving the Kolmogorov PDE by means of deep learning
From MaRDI portal
Publication:2051092
PDEs with randomness, stochastic partial differential equations (35R60) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Neural nets and related approaches to inference from stochastic processes (62M45) Numerical solutions to stochastic differential and integral equations (65C30) Artificial neural networks and deep learning (68T07)
Abstract: Stochastic differential equations (SDEs) and the Kolmogorov partial differential equations (PDEs) associated to them have been widely used in models from engineering, finance, and the natural sciences. In particular, SDEs and Kolmogorov PDEs, respectively, are highly employed in models for the approximative pricing of financial derivatives. Kolmogorov PDEs and SDEs, respectively, can typically not be solved explicitly and it has been and still is an active topic of research to design and analyze numerical methods which are able to approximately solve Kolmogorov PDEs and SDEs, respectively. Nearly all approximation methods for Kolmogorov PDEs in the literature suffer under the curse of dimensionality or only provide approximations of the solution of the PDE at a single fixed space-time point. In this paper we derive and propose a numerical approximation method which aims to overcome both of the above mentioned drawbacks and intends to deliver a numerical approximation of the Kolmogorov PDE on an entire region without suffering from the curse of dimensionality. Numerical results on examples including the heat equation, the Black-Scholes model, the stochastic Lorenz equation, and the Heston model suggest that the proposed approximation algorithm is quite effective in high dimensions in terms of both accuracy and speed.
Recommendations
- Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
Cites work
- A distribution-free theory of nonparametric regression
- A note on tamed Euler approximations
- 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
- Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
- Compact finite difference method for American option pricing
- Continuous Markov processes and stochastic equations
- Convergence rates for the stochastic gradient descent method for non-convex objective functions
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep Neural Network Approximation Theory
- Deep optimal stopping
- Euler approximations with varying coefficients: the case of superlinearly growing diffusion coefficients
- Exponential integrability properties of numerical approximation processes for nonlinear stochastic differential equations
- Finite difference methods for the weak solutions of the Kolmogorov equation for the density of both diffusion and conditional diffusion processes
- Finite element method. Vol. 1: The basis.
- General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
- scientific article; zbMATH DE number 3126094 (Why is no real title available?)
- scientific article; zbMATH DE number 44054 (Why is no real title available?)
- scientific article; zbMATH DE number 54145 (Why is no real title available?)
- scientific article; zbMATH DE number 1478492 (Why is no real title available?)
- scientific article; zbMATH DE number 2114382 (Why is no real title available?)
- scientific article; zbMATH DE number 6159604 (Why is no real title available?)
- Hypoelliptic second order differential equations
- Infinite dimensional analysis. A hitchhiker's guide.
- Loss of regularity for Kolmogorov equations
- Lower error bounds for the stochastic gradient descent optimization algorithm: sharp convergence rates for slowly and fast decaying learning rates
- Minimal Errors for Strong and Weak Approximation of Stochastic Differential Equations
- Multilevel Monte Carlo Path Simulation
- Numerical approximations of stochastic differential equations with non-globally Lipschitz continuous coefficients
- Numerical Integration of Stochastic Differential Equations with Nonglobally Lipschitz Coefficients
- Numerical solution of SDE through computer experiments. Including floppy disk
- On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
- On the discretization schemes for the CIR (and Bessel squared) processes
- On the mathematical foundations of learning
- Optimal approximation with sparsely connected deep neural networks
- Pattern recognition and machine learning.
- Probability theory. A comprehensive course
- Solving high-dimensional partial differential equations using deep learning
- Stochastic differential equations. An introduction with applications.
- Stochastic simulation and Monte Carlo methods. Mathematical foundations of stochastic simulation
- Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients
- Strong convergence of full-discrete nonlinearity-truncated accelerated exponential Euler-type approximations for stochastic Kuramoto-Sivashinsky equations
- Strong convergence rates for Cox-Ingersoll-Ross processes -- full parameter range
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- Understanding machine learning. From theory to algorithms
Cited in
(68)- 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
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- Approximation spaces of deep neural networks
- 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
- A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions
- Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
- A numerical approach to Kolmogorov equation in high dimension based on Gaussian analysis
- Physics informed by deep learning: numerical solutions of modified Korteweg-de Vries equation
- Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- A new method for solving Kolmogorov equations in mathematical finance
- Analytical solutions to the backward Kolmogorov PDE via an adiabatic approximation to the Schrödinger PDE
- Probability measure-valued polynomial diffusions
- Numerical computation of probabilities for nonlinear SDEs in high dimension using Kolmogorov equation
- Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
- Space-time error estimates for deep neural network approximations for differential equations
- 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
- Deep splitting method for parabolic PDEs
- Higher-order quasi-Monte Carlo training of 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
- Approximations with deep neural networks in Sobolev time-space
- Full error analysis for the training of deep neural networks
- An unsupervised deep learning approach to solving partial integro-differential equations
- Unbiased deep solvers for linear parametric PDEs
- Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
- Approximative policy iteration for exit time feedback control problems driven by stochastic differential equations using tensor train format
- 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
- DEEP EQUILIBRIUM NETS
- Artificial neural network solver for time-dependent Fokker-Planck equations
- Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning
- A deep learning approach to the probabilistic numerical solution of path-dependent partial 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
- Enhancing physics informed neural networks for solving Navier-Stokes equations
- Deep learning based on randomized quasi-Monte Carlo method for solving linear Kolmogorov partial differential equation
- Deep neural networks for probability of default modelling
- Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
- Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
- Time integration schemes based on neural networks for solving partial differential equations on coarse grids
- Generalization error analysis of deep backward dynamic programming for solving nonlinear PDEs
- Bounds on the approximation error for deep neural networks applied to dispersive models: nonlinear waves
- Deep Picard iteration for high-dimensional nonlinear PDEs
- Space-time deep neural network approximations for high-dimensional partial differential equations
- Error bound analysis of physics-informed neural networks for solving nonlinear projection equations
- Deep-time neural networks: an efficient approach for solving high-dimensional PDEs
- Some thoughts on compositional tensor networks
- An uncertainty-aware, mesh-free numerical method for Kolmogorov PDEs
- Compositional sparsity, approximation classes, and parametric transport equations
- Full error analysis of the random deep splitting method for nonlinear parabolic PDEs and PIDEs
- Solving high-dimensional Kolmogorov backward equations with functional hierarchical tensor operators
- Convergence analysis of the deep splitting scheme: the case of partial integro-differential equations and the associated forward backward SDEs with jumps
- SFVnet: finite-volume informed U-Net for compressible flow prediction with sparse data under ill-conditions
- A deep solver for backward stochastic Volterra integral equations
- Extended Walk-on-Spheres Algorithm for Linear and Nonlinear Elliptic Problems of Divergence-type
- Numerical analysis of residual neural networks for stochastic partial differential equations
- Polynomial-augmented neural networks (PANNs) with weak orthogonality constraints for enhanced function and PDE approximation
- Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
This page was built for publication: Solving the Kolmogorov PDE by means of deep learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2051092)
