A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations

DOI10.1090/memo/1410OpenAlexW2890889625MaRDI QIDQ5889064

Philippe von Wurstemberger, Fabian Hornung, Arnulf Jentzen, Philipp Grohs

Publication date: 26 April 2023

Published in: Memoirs of the American Mathematical Society (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.02362

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to numerical analysis (65-02) Stochastic analysis (60Hxx) Numerical approximation and computational geometry (primarily algorithms) (65D99) Parabolic equations and parabolic systems (35Kxx)

Related Items (16)

Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data ⋮ An efficient Monte Carlo scheme for Zakai equations ⋮ Monte Carlo simulation of SDEs using GANs ⋮ Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes ⋮ A Kolmogorov-Chentsov type theorem on general metric spaces with applications to limit theorems for Banach-valued processes ⋮ Numerical methods for backward stochastic differential equations: a survey ⋮ Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus ⋮ How many inner simulations to compute conditional expectations with least-square Monte Carlo? ⋮ Applications of artificial neural networks to simulating Lévy processes ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data ⋮ Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks ⋮ On existence and uniqueness properties for solutions of stochastic fixed point equations ⋮ Deep Splitting Method for Parabolic PDEs ⋮ 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

Uses Software

• ImageNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Breaking the curse of dimensionality in sparse polynomial approximation of parametric PDEs
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Infinite-dimensional quadrature and approximation of distributions
• Geometric theory of semilinear parabolic equations
• Monte Carlo complexity of global solution of integral equations
• Approximation and estimation bounds for artificial neural networks
• Multilayer feedforward networks are universal approximators
• Nesting Monte Carlo for high-dimensional non-linear PDEs
• Provable approximation properties for deep neural networks
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Degree of approximation by neural and translation networks with a single hidden layer
• Approximation of functions and their derivatives: A neural network implementation with applications
• Existence, uniqueness, and regularity for stochastic evolution equations with irregular initial values
• Topological properties of the set of functions generated by neural networks of fixed size
• Solving the Kolmogorov PDE by means of deep learning
• Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
• Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
• DNN expression rate analysis of high-dimensional PDEs: application to option pricing
• A theoretical analysis of deep neural networks and parametric PDEs
• Universal approximations of invariant maps by neural networks
• Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Error bounds for approximations with deep ReLU networks
• A machine learning framework for data driven acceleration of computations of differential equations
• Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Loss of regularity for Kolmogorov equations
• Stochastic simulation and Monte Carlo methods. Mathematical foundations of stochastic simulation
• Runge-Kutta schemes for backward stochastic differential equations
• A regression-based Monte Carlo method to solve backward stochastic differential equations
• Space-time error estimates for deep neural network approximations for differential equations
• Stratified Regression Monte-Carlo Scheme for Semilinear PDEs and BSDEs with Large Scale Parallelization on GPUs
• Deep vs. shallow networks: An approximation theory perspective
• Multilevel Monte Carlo Path Simulation
• Viscosity Solutions of Hamilton-Jacobi Equations
• User’s guide to viscosity solutions of second order partial differential equations
• Universal approximation bounds for superpositions of a sigmoidal function
• Neural Networks for Localized Approximation
• Foundations of Modern Probability
• Book Reviews
• Convergence in Hölder norms with applications to Monte Carlo methods in infinite dimensions
• Solving high-dimensional partial differential equations using deep learning
• Solving parametric PDE problems with artificial neural networks
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
• Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
• Decoupling on the Wiener Space, Related Besov Spaces, and Applications to BSDEs
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• Approximation of high-dimensional parametric PDEs
• Numerical solution of parabolic equations in high dimensions
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Deep optimal stopping
• A logical calculus of the ideas immanent in nervous activity
• Probability theory. A comprehensive course
• Approximation by superpositions of a sigmoidal function
• Error bounds for approximation with neural networks
• Stochastic Equations in Infinite Dimensions

This page was built for publication: A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations