A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations

Abstract

Artificial neural networks (ANNs) have very successfully been used in numerical simulations for a series of computational problems ranging from image classification/image recognition, speech recognition, time series analysis, game intelligence, and computational advertising to numerical approximations of partial differential equations (PDEs). Such numerical simulations suggest that ANNs have the capacity to very efficiently approximate high-dimensional functions and, especially, indicate that ANNs seem to admit the fundamental power to overcome the curse of dimensionality when approximating the high-dimensional functions appearing in the above named computational problems. There are a series of rigorous mathematical approximation results for ANNs in the scientific literature. Some of them prove convergence without convergence rates and some even rigorously establish convergence rates but there are only a few special cases where mathematical results can rigorously explain the empirical success of ANNs when approximating high-dimensional functions. The key contribution of this article is to disclose that ANNs can efficiently approximate high-dimensional functions in the case of numerical approximations of Black-Scholes PDEs. More precisely, this work reveals that the number of required parameters of an ANN to approximate the solution of the Black-Scholes PDE grows at most polynomially in both the reciprocal of the prescribed approximation accuracy $\epsilon >0$ and the PDE dimension $d\in \mathbb{N}$. We thereby prove, for the first time, that ANNs do indeed overcome the curse of dimensionality in the numerical approximation of Black-Scholes PDEs.

arXiv commentTo appear in Mem. Amer. Math. Soc.; 126 pages

References in corpus (27)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• A regression-based Monte Carlo method to solve backward stochastic differential equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Provable approximation properties for deep neural networks
• Solving parametric PDE problems with artificial neural networks
• DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Loss of regularity for Kolmogorov equations
• Solving the Kolmogorov PDE by means of deep learning
• Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
• Local Lipschitz continuity in the initial value and strong completeness for nonlinear stochastic differential equations
• Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
• Stratified regression Monte-Carlo scheme for semilinear PDEs and BSDEs with large scale parallelization on GPUs
• A 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
• Runge-Kutta schemes for backward stochastic differential equations
• Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
• Convergence in Hölder norms with applications to Monte Carlo methods in infinite dimensions
• Deep neural network approximations for Monte Carlo algorithms
• Existence, uniqueness, and regularity for stochastic evolution equations with irregular initial values
• The universal approximation power of finite-width deep ReLU networks

Cited by in corpus (53)

• DeepXDE: A deep learning library for solving differential equations
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• 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
• 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
• Convergence of the Deep BSDE Method for Coupled FBSDEs
• The Modern Mathematics of Deep Learning
• DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing
• An overview on deep learning-based approximation methods for partial differential equations
• A novel meta-learning initialization method for physics-informed neural networks
• Solving Forward and Inverse Problems of Contact Mechanics using Physics-Informed Neural Networks
• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks
• Full error analysis for the training of deep neural networks
• Efficient approximation of high-dimensional functions with neural networks
• Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
• Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
• Uniform error estimates for artificial neural network approximations for heat equations
• Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
• Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks
• A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
• Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
• Generalised multilevel Picard approximations
• Some observations on high-dimensional partial differential equations with Barron data
• The gap between theory and practice in function approximation with deep neural networks
• Towards a regularity theory for ReLU networks -- chain rule and global error estimates
• Multilevel Picard approximations for high-dimensional semilinear second-order PDEs with Lipschitz nonlinearities
• NeuralPDE: Automating Physics-Informed Neural Networks (PINNs) with Error Approximations
• A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation models
• On the Representation of Solutions to Elliptic PDEs in Barron Spaces
• On existence and uniqueness properties for solutions of stochastic fixed point equations
• Unbiased deep solvers for linear parametric PDEs
• Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast, Differentiable Fluid Models that Generalize
• Random feature neural networks learn Black-Scholes type PDEs without curse of dimensionality
• High-dimensional approximation spaces of artificial neural networks and applications to partial differential equations
• Parametric Complexity Bounds for Approximating PDEs with Neural Networks
• Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
• Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data
• A stochastic Gronwall inequality and applications to moments, strong completeness, strong local Lipschitz continuity, and perturbations
• Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
• Multilevel Monte-Carlo for computing the SCR with the standard formula and other stress tests
• Error bounds for PDE-regularized learning
• An efficient Monte Carlo scheme for Zakai equations
• Strong overall error analysis for the training of artificial neural networks via random initializations
• Monte Carlo Simulation of SDEs using GANs
• On the space-time expressivity of ResNets
• (Thesis) Reservoir Computing With Dynamical Systems
• XNet-Enhanced Deep BSDE Method and Numerical Analysis
• Deep Learning for Constrained Utility Maximisation
• Strong convergence rate of Euler-Maruyama approximations in temporal-spatial Hölder-norms
• Strong $L^p$-error analysis of nonlinear Monte Carlo approximations for high-dimensional semilinear partial differential equations
• Review: Ordinary Differential Equations For Deep Learning