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
From MaRDI portal
Publication:5037569
Abstract: The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined deep learning, revolutionized the area of artificial intelligence, machine learning, and data analysis. In particular, these methods have been applied to the numerical solution of high-dimensional partial differential equations with great success. Recent simulations indicate that deep learning-based algorithms are capable of overcoming the curse of dimensionality for the numerical solution of Kolmogorov equations, which are widely used in models from engineering, finance, and the natural sciences. The present paper considers under which conditions ERM over a deep neural network hypothesis class approximates the solution of a -dimensional Kolmogorov equation with affine drift and diffusion coefficients and typical initial values arising from problems in computational finance up to error . We establish that, with high probability over draws of training samples, such an approximation can be achieved with both the size of the hypothesis class and the number of training samples scaling only polynomially in and . It can be concluded that ERM over deep neural network hypothesis classes overcomes the curse of dimensionality for the numerical solution of linear Kolmogorov equations with affine coefficients.
Recommendations
- 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
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- Solving the Kolmogorov PDE by means of deep learning
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
Cites work
- scientific article; zbMATH DE number 3438157 (Why is no real title available?)
- scientific article; zbMATH DE number 1420699 (Why is no real title available?)
- scientific article; zbMATH DE number 5681750 (Why is no real title available?)
- scientific article; zbMATH DE number 7064043 (Why is no real title available?)
- A distribution-free theory of nonparametric regression
- A mean field view of the landscape of two-layer neural networks
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- DGM: a deep learning algorithm for solving partial differential equations
- Deep Neural Network Approximation Theory
- 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
- Deep optimal stopping
- Error bounds for approximation with neural networks
- Error bounds for approximations with deep ReLU networks
- Foundations of machine learning
- Infinite dimensional analysis. A hitchhiker's guide.
- Learning Theory
- Local Rademacher complexities
- 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
- Neural Network Learning
- On the mathematical foundations of learning
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Optimal approximation with sparsely connected deep neural networks
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- 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
- Provable approximation properties for deep neural networks
- 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 the Kolmogorov PDE by means of deep learning
- Stochastic simulation and Monte Carlo methods. Mathematical foundations of stochastic simulation
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- Tools for computational finance.
- Topological properties of the set of functions generated by neural networks of fixed size
Cited in
(70)- Deep empirical risk minimization in finance: Looking into the future
- Non intrusive reduced order modeling of parametrized PDEs by kernel POD and neural networks
- Non-linear interactions and exchange rate prediction: empirical evidence using support vector regression
- 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
- 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
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- Uniform error estimates for artificial neural network approximations for heat equations
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- 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
- Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
- Three ways to solve partial differential equations with neural networks — A review
- Sparse polynomial approximations for affine parametric saddle point problems
- Deep learning based on randomized quasi-Monte Carlo method for solving linear Kolmogorov partial differential equation
- Error analysis for deep neural network approximations of parametric hyperbolic conservation laws
- An overview on deep learning-based approximation methods for partial differential equations
- 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
- Solving the Kolmogorov PDE by means of deep learning
- Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces
- Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks
- Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
- A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for deep BSDE solver
- Metric entropy limits on recurrent neural network learning of linear dynamical systems
- Generalization of PINNs for elliptic interface problems
- Error estimates for deep learning methods in fluid dynamics
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms
- Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
- Enhancing the momentum strategy through deep regression
- Imaging conductivity from current density magnitude using neural networks
- Computing Lyapunov functions using deep neural networks
- Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
- Neural network approximation and estimation of classifiers with classification boundary in a Barron class
- Convergence of a Robust Deep FBSDE Method for Stochastic Control
- Strong overall error analysis for the training of artificial neural networks via random initializations
- Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
- Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
- Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
- Quantitative Approximation Results for Complex-Valued Neural Networks
- Deep neural network surrogates for nonsmooth quantities of interest in shape uncertainty quantification
- Monte Carlo simulation of SDEs using GANs
- Convergence bounds for empirical nonlinear least-squares
- Physics and equality constrained artificial neural networks: application to forward and inverse problems with multi-fidelity data fusion
- Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN
- Convergence of Physics-Informed Neural Networks Applied to Linear Second-Order Elliptic Interface Problems
- 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
- Active learning based sampling for high-dimensional nonlinear partial differential equations
- A theoretical analysis of deep neural networks and parametric PDEs
- Sampling complexity of deep approximation spaces
- Space-time error estimates for deep neural network approximations for differential equations
- Optimally weighted loss functions for solving PDEs with neural networks
- Solving PDEs on unknown manifolds with machine learning
- Numerical methods for backward stochastic differential equations: a survey
- 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
- RICAM, the Johann Radon Institute for Computational and Applied Mathematics
- 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
- Adaptive neural network surrogate model for solving the implied volatility of time-dependent American option via Bayesian inference
- Greedy training algorithms for neural networks and applications to PDEs
- Exponential ReLU neural network approximation rates for point and edge singularities
- Deep splitting method for parabolic PDEs
- An extreme learning machine-based method for computational PDEs in higher dimensions
- Error analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEs
This page was built for publication: 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
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037569)
