DNN expression rate analysis of high-dimensional PDEs: application to option pricing

DOI10.1007/S00365-021-09541-6MaRDI QIDQ2117328zbMATH OpenOpenAlexWikidataFDO

Authors Dennis Elbrächter, Philipp Grohs, Arnulf Jentzen, Christoph Schwab

Publication date 21 March 2022

Published in Constructive Approximation (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1809.07669

zbMATH Keywords

option pricinglow-rank approximationneural network approximationhigh-dimensional PDEs

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) Numerical integration (65D30) Second-order parabolic equations (35K10) Theoretical approximation in context of PDEs (35A35) PDEs on graphs and networks (ramified or polygonal spaces) (35R02) Weighted approximation (41A81)

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 $varepsilon$-error by a deep ReLU network with depth $$ and $$ non-zero weights, where $ninmathbbN$ is arbitrary (with the constant implied in $mathcalO(cdot)$ 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.

Recommendations

• Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models
• Deep ReLU networks and high-order finite element methods
• The deep parametric PDE method and applications to option pricing
• Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
• Constructive deep ReLU neural network approximation

Cites work

• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• A machine learning framework for data driven acceleration of computations of differential equations
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat 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
• Approximation by superpositions of a sigmoidal function
• Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
• DGM: a deep learning algorithm for solving partial differential equations
• Deep Neural Network Approximation Theory
• Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models
• Deep learning
• Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Error bounds for approximations with deep ReLU networks
• Functional Integration and Partial Differential Equations. (AM-109)
• Loss of regularity for Kolmogorov equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Machine learning for pricing American options in high-dimensional Markovian and non-Markovian models
• Mathematical models of financial derivatives
• Neural Networks for Localized Approximation
• Nonparametric regression using deep neural networks with ReLU activation function
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Optimal approximation with sparsely connected deep neural networks
• Paul Wilmott introduces quantitative finance. With CD-ROM
• 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
• Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
• Solving high-dimensional partial differential equations using deep learning
• Solving parametric PDE problems with artificial neural networks
• Solving the Kolmogorov PDE by means of deep learning
• The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(43)

• Unbiased deep solvers for linear parametric PDEs
• Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models
• Full error analysis for the training of deep neural networks
• Solving parametric partial differential equations with deep rectified quadratic unit neural networks
• A measure theoretical approach to the mean-field maximum principle for training NeurODEs
• Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples
• Deep neural network expressivity for optimal stopping problems
• Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
• A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
• Deep ReLU networks and high-order finite element methods. II: Chebyšev emulation
• An overview on deep learning-based approximation methods for partial differential equations
• Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
• Mesh-informed neural networks for operator learning in finite element spaces
• Approximation rates for deep calibration of (rough) stochastic volatility models
• Neural network approximation and estimation of classifiers with classification boundary in a Barron class
• Approximation properties of residual neural networks for Kolmogorov PDEs
• Convergence of a Robust Deep FBSDE Method for Stochastic Control
• Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
• Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
• Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
• Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
• A New Certified Hierarchical and Adaptive RB-ML-ROM Surrogate Model for Parametrized PDEs
• The deep parametric PDE method and applications to option pricing
• Deep Curve-Dependent PDEs for Affine Rough Volatility
• Information theory and recovery algorithms for data fusion in Earth observation
• Spectral operator learning for parametric PDEs without data reliance
• Neural Network Approximation of Coarse-Scale Surrogates in Numerical Homogenization
• Parameter identification by deep learning of a material model for granular media
• Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
• Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
• Long-time integration of parametric evolution equations with physics-informed DeepONets
• Space-time error estimates for deep neural network approximations for differential equations
• Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations
• Multilevel Picard approximations of high-dimensional semilinear partial differential equations with locally monotone coefficient functions
• Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations
• Approximations with deep neural networks in Sobolev time-space
• Error analysis for empirical risk minimization over clipped ReLU networks in solving linear Kolmogorov partial differential equations
• Simultaneous neural network approximation for smooth functions
• Detecting asset price bubbles using deep learning
• Exponential ReLU neural network approximation rates for point and edge singularities
• Deep splitting method for parabolic PDEs
• Numerical investigation of high-dimensional option pricing PDEs by utilizing a hybrid radial basis function -- finite difference procedure
• Neural network expression rates and applications of the deep parametric PDE method in counterparty credit risk

Describes a project that uses

Uses Software

• DGM

This page was built for publication: DNN expression rate analysis of high-dimensional PDEs: application to option pricing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117328)