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

DOI10.1137/19M125649XzbMath1480.60191arXiv1809.03062MaRDI QIDQ5037569

Arnulf Jentzen, Julius Berner, Philipp Grohs

Publication date: 1 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.03062




Related Items (52)

Convergence bounds for empirical nonlinear least-squaresNon intrusive reduced order modeling of parametrized PDEs by kernel POD and neural networksConvergence of a Robust Deep FBSDE Method for Stochastic ControlConvergence of Physics-Informed Neural Networks Applied to Linear Second-Order Elliptic Interface ProblemsA new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for deep BSDE solverMetric entropy limits on recurrent neural network learning of linear dynamical systemsError estimates for deep learning methods in fluid dynamicsDeep neural network approximations for solutions of PDEs based on Monte Carlo algorithmsQuantitative Approximation Results for Complex-Valued Neural NetworksOvercoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearitiesApproximations with deep neural networks in Sobolev time-spaceImaging conductivity from current density magnitude using neural networks*Full error analysis for the training of deep neural networksUnbiased Deep Solvers for Linear Parametric PDEsTowards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WANPhysics and equality constrained artificial neural networks: application to forward and inverse problems with multi-fidelity data fusionDeep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty QuantificationSimultaneous neural network approximation for smooth functionsThree ways to solve partial differential equations with neural networks — A reviewMonte Carlo simulation of SDEs using GANsSparse polynomial approximations for affine parametric saddle point problemsPhysics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithmsSolving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemesExponential ReLU neural network approximation rates for point and edge singularitiesOverall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisationActive learning based sampling for high-dimensional nonlinear partial differential equationsSpace-time error estimates for deep neural network approximations for differential equationsAn extreme learning machine-based method for computational PDEs in higher dimensionsLower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionalityNumerical methods for backward stochastic differential equations: a surveyNeural network approximation and estimation of classifiers with classification boundary in a Barron classDeep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov EquationsSolving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculusOvercoming the curse of dimensionality in the approximative pricing of financial derivatives with default risksAdaptive neural network surrogate model for solving the implied volatility of time-dependent American option via Bayesian inferenceAn overview on deep learning-based approximation methods for partial differential equationsGreedy training algorithms for neural networks and applications to PDEsNon-Linear Interactions and Exchange Rate Prediction: Empirical Evidence Using Support Vector RegressionDeep ReLU network expression rates for option prices in high-dimensional, exponential Lévy modelsDeep Splitting Method for Parabolic PDEsComputing Lyapunov functions using deep neural networksSolving the Kolmogorov PDE by means of deep learningVariational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equationsOptimally weighted loss functions for solving PDEs with neural networksEnhancing the momentum strategy through deep regressionRICAM, the Johann Radon Institute for Computational and Applied MathematicsError analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEsStable recovery of entangled weights: towards robust identification of deep neural networks from minimal samplesA measure theoretical approach to the mean-field maximum principle for training NeurODEsAlgorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learningDNN expression rate analysis of high-dimensional PDEs: application to option pricingA theoretical analysis of deep neural networks and parametric PDEs


Uses Software


Cites Work


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