Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems

Abstract

In this paper, we establish that for a wide class of controlled stochastic differential equations (SDEs) with stiff coefficients, the value functions of corresponding zero-sum games can be represented by a deep artificial neural network (DNN), whose complexity grows at most polynomially in both the dimension of the state equation and the reciprocal of the required accuracy. Such nonlinear stiff systems may arise, for example, from Galerkin approximations of controlled stochastic partial differential equations (SPDEs), or controlled PDEs with uncertain initial conditions and source terms. This implies that DNNs can break the curse of dimensionality in numerical approximations and optimal control of PDEs and SPDEs. The main ingredient of our proof is to construct a suitable discrete-time system to effectively approximate the evolution of the underlying stochastic dynamics. Similar ideas can also be applied to obtain expression rates of DNNs for value functions induced by stiff systems with regime switching coefficients and driven by general Lévy noise.

arXiv commentThis revised version has been accepted for publication in Analysis and Applications

References in corpus (7)

• Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• Deep Learning Approximation for Stochastic Control Problems
• DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing
• Adaptive Euler-Maruyama Method for SDEs with Non-globally Lipschitz Drift: Part I, Finite Time Interval
• A neural network based policy iteration algorithm with global $H^2$-superlinear convergence for stochastic games on domains
• Deep backward schemes for high-dimensional nonlinear PDEs

Cited by in corpus (17)

• 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
• An overview on deep learning-based approximation methods for partial differential equations
• On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton--Jacobi 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
• 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
• Generalised multilevel Picard approximations
• Multilevel Picard approximations for high-dimensional semilinear second-order PDEs with Lipschitz nonlinearities
• Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
• Random feature neural networks learn Black-Scholes type PDEs without curse of dimensionality
• Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
• High-dimensional approximation spaces of artificial neural networks and applications to partial differential equations
• Lax-Oleinik-type formulas and efficient algorithms for certain high-dimensional optimal control problems
• Review: Ordinary Differential Equations For Deep Learning
• Hopf-type representation formulas and efficient algorithms for certain high-dimensional optimal control problems