DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing

Abstract

We analyze approximation rates by deep ReLU networks of a class of multi-variate solutions of Kolmogorov equations which arise in option pricing. Key technical devices are deep ReLU architectures capable of efficiently approximating tensor products. Combining this with results concerning the approximation of well behaved (i.e. fulfilling some smoothness properties) univariate functions, this provides insights into rates of deep ReLU approximation of multi-variate functions with tensor structures. We apply this in particular to the model problem given by the price of a European maximum option on a basket of $d$ assets within the Black-Scholes model for European maximum option pricing. We prove that the solution to the $d$-variate option pricing problem can be approximated up to an $\epsilon$-error by a deep ReLU network with depth $\mathcal{O}(\ln (d)\ln ({\epsilon }^{-1})+\ln (d{)}^2)$ and $\mathcal{O}\left(d^{2+\frac{1}{n}}{\epsilon }^{-\frac{1}{n}}\right)$ non-zero weights, where $n\in \mathbb{N}$ is arbitrary (with the constant implied in $\mathcal{O}(\cdot )$ depending on $n$). The techniques developed in the constructive proof are of independent interest in the analysis of the expressive power of deep neural networks for solution manifolds of PDEs in high dimension.

References in corpus (4)

• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• 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
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Uniform error estimates for artificial neural network approximations for heat equations

Cited by in corpus (22)

• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• The Modern Mathematics of Deep Learning
• An overview on deep learning-based approximation methods for partial differential equations
• Full error analysis for the training of deep 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
• Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
• A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for Deep BSDE solver
• Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities
• Deep neural network approximations for Monte Carlo algorithms
• Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons
• Generalised multilevel Picard approximations
• 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
• Unbiased deep solvers for linear parametric PDEs
• Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
• A Measure Theoretical Approach to the Mean-field Maximum Principle for Training NeurODEs
• Deep ReLU networks and high-order finite element methods II: Chebyshev emulation
• Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network