Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations

From MaRDI portal

Publication:2327815

Jump to:navigation, search

DOI10.1007/s00332-018-9525-3zbMath1442.91116arXiv1709.05963OpenAlexW2754833785WikidataQ128616163 ScholiaQ128616163MaRDI QIDQ2327815

Arnulf Jentzen, Christian Beck, E. Weinan

Publication date: 8 October 2019

Published in: Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1709.05963

zbMATH Keywords

numerical method Black-Scholes-Barenblatt equation HJB equation Knightian uncertainty \(G\)-Brownian motion nonlinear expectation deep learning Hamiltonian-Jacobi-Bellman equation 2BSDE second-order backward stochastic differential equation

Mathematics Subject Classification ID

Numerical methods (including Monte Carlo methods) (91G60) Derivative securities (option pricing, hedging, etc.) (91G20) Stochastic partial differential equations (aspects of stochastic analysis) (60H15) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75)

Related Items (only showing first 100 items - show all)

Numerical methods for backward stochastic differential equations: a survey ⋮ Stability of backward stochastic differential equations: the general Lipschitz case ⋮ Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations ⋮ A deep-genetic algorithm (deep-GA) approach for high-dimensional nonlinear parabolic partial differential equations ⋮ Neural Control of Parametric Solutions for High-Dimensional Evolution PDEs ⋮ A deep branching solver for fully nonlinear partial differential equations ⋮ Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions ⋮ Unnamed Item ⋮ $\alpha$-Hypergeometric Uncertain Volatility Models and their Connection to 2BSDEs ⋮ Solving forward and inverse problems of the logarithmic nonlinear Schrödinger equation with \(\mathcal{PT}\)-symmetric harmonic potential via deep learning ⋮ On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton-Jacobi partial differential equations ⋮ A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables ⋮ 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 ⋮ Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space ⋮ Convergence of a Robust Deep FBSDE Method for Stochastic Control ⋮ A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations ⋮ PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries ⋮ Analytic continuation of noisy data using Adams Bashforth residual neural network ⋮ PFNN-2: A Domain Decomposed Penalty-Free Neural Network Method for Solving Partial Differential Equations ⋮ MIM: a deep mixed residual method for solving high-order partial differential equations ⋮ Meta-mgnet: meta multigrid networks for solving parameterized partial differential equations ⋮ A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder ⋮ IGA-reuse-NET: a deep-learning-based isogeometric analysis-reuse approach with topology-consistent parameterization ⋮ Gradient boosting-based numerical methods for high-dimensional backward stochastic differential equations ⋮ Solving Fredholm integral equations using deep learning ⋮ Error estimates for deep learning methods in fluid dynamics ⋮ Deep learning for constrained utility maximisation ⋮ Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms ⋮ The deep parametric PDE method and applications to option pricing ⋮ Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities ⋮ Convergence Rate Analysis for Deep Ritz Method ⋮ Multilevel Picard approximations of high-dimensional semilinear partial differential equations with locally monotone coefficient functions ⋮ State-Dependent Temperature Control for Langevin Diffusions ⋮ Data-driven rogue waves and parameters discovery in nearly integrable \(\mathcal{PT}\)-symmetric Gross-Pitaevskii equations via PINNs deep learning ⋮ Convergence of deep fictitious play for stochastic differential games ⋮ Full error analysis for the training of deep neural networks ⋮ Adaptive deep neural networks methods for high-dimensional partial differential equations ⋮ Sufficient and necessary conditions of near-optimal controls for a diffusion dengue model with Lévy noise ⋮ Numerical computation of probabilities for nonlinear SDEs in high dimension using Kolmogorov equation ⋮ Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning ⋮ Learning-based local weighted least squares for algebraic multigrid method ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Multi-fidelity surrogate modeling using long short-term memory networks ⋮ Numerical solution of the modified and non-Newtonian Burgers equations by stochastic coded trees ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes ⋮ New regularity estimates for fully nonlinear elliptic equations ⋮ Accuracy and architecture studies of residual neural network method for ordinary differential equations ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ Exponential Convergence of Deep Operator Networks for Elliptic Partial Differential Equations ⋮ The Kolmogorov infinite dimensional equation in a Hilbert space via deep learning methods ⋮ A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations ⋮ Space-time error estimates for deep neural network approximations for differential equations ⋮ ADLGM: an efficient adaptive sampling deep learning Galerkin method ⋮ An extreme learning machine-based method for computational PDEs in higher dimensions ⋮ Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs ⋮ Numerical resolution of McKean-Vlasov FBSDEs using neural networks ⋮ A Normalizing Field Flow Induced Two-Stage Stochastic Homogenization Method for Random Composite Materials ⋮ Deep neural networks learning forward and inverse problems of two-dimensional nonlinear wave equations with rational solitons ⋮ Less is more: a new machine-learning methodology for spatiotemporal systems ⋮ A fully nonlinear Feynman-Kac formula with derivatives of arbitrary orders ⋮ Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks ⋮ Stochastic Methods for Solving High-Dimensional Partial Differential Equations ⋮ Approximation properties of residual neural networks for Kolmogorov PDEs ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ A numerical approach to Kolmogorov equation in high dimension based on Gaussian analysis ⋮ A Unified Probabilistic Discretization Scheme for FBSDEs: Stability, Consistency, and Convergence Analysis ⋮ Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ ⋮ A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations ⋮ Deep ReLU networks and high-order finite element methods ⋮ Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems ⋮ Numerical solution of inverse problems by weak adversarial networks ⋮ Convergence of the deep BSDE method for coupled FBSDEs ⋮ Optimizing a portfolio of mean-reverting assets with transaction costs via a feedforward neural network ⋮ DeepXDE: A Deep Learning Library for Solving Differential Equations ⋮ The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems ⋮ An analysis of asymptotic properties and error control under the exponential jump-diffusion model for American option pricing ⋮ Addressing the curse of dimensionality in stochastic dynamics: a Wiener path integral variational formulation with free boundaries ⋮ Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations ⋮ Numerical Simulations for Full History Recursive Multilevel Picard Approximations for Systems of High-Dimensional Partial Differential Equations ⋮ Neural networks-based backward scheme for fully nonlinear PDEs ⋮ Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations ⋮ Tractability for Volterra problems of the second kind with convolution kernels ⋮ Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning ⋮ Deep Splitting Method for Parabolic PDEs ⋮ Deep backward schemes for high-dimensional nonlinear PDEs ⋮ Numerical solution of the parametric diffusion equation by deep neural networks ⋮ Approximation rates for neural networks with encodable weights in smoothness spaces ⋮ A Multiscale Neural Network Based on Hierarchical Matrices ⋮ Pricing equity-linked life insurance contracts with multiple risk factors by neural networks ⋮ Limits of random walks with distributionally robust transition probabilities ⋮ Explicit deferred correction methods for second-order forward backward stochastic differential equations ⋮ Machine learning for semi linear PDEs ⋮ A Stochastic Gradient Descent Approach for Stochastic Optimal Control ⋮ A multiscale neural network based on hierarchical nested bases ⋮ Stability analysis of hierarchical tensor methods for time-dependent PDEs ⋮ Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs ⋮ Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures ⋮ High order one-step methods for backward stochastic differential equations via Itô-Taylor expansion ⋮ Efficient coupled deep neural networks for the time-dependent coupled Stokes-Darcy problems

Uses Software

Cites Work

This page was built for publication: Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Publication:2327815&oldid=14918933"