Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations

DOI10.1142/S0219530522500129OpenAlexW3163741067WikidataQ114072416 ScholiaQ114072416MaRDI QIDQ5873924

Christoph Schwab, Lukas Gonon

Publication date: 10 February 2023

Published in: Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.11707

zbMATH Keywords

option pricingcurse of dimensionalityjump-diffusion processdeep neural networkpartial integrodifferential equationexpression rate

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Integro-partial differential equations (45K05) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)

Related Items

Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Feynman-Kac-type formula for Lévy processes with discontinuous killing rates
• Numerical methods for Lévy processes
• Numerical solution of stochastic differential equations with jumps in finance
• Stochastic differential equations of jump type and Lévy processes in diffeomorphisms group
• On best approximation by ridge functions
• The Euler scheme for Lévy driven stochastic differential equations
• Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
• DNN expression rate analysis of high-dimensional PDEs: application to option pricing
• The Barron space and the flow-induced function spaces for neural network models
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Machine learning for fast and reliable solution of time-dependent differential equations
• Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels
• Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models
• Strong convergence of the Euler-Maruyama approximation for a class of Lévy-driven SDEs
• Error bounds for approximations with deep ReLU networks
• On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
• Feynman-Kac representation for Hamilton-Jacobi-Bellman IPDE
• Numerical methods for nonlinear stochastic differential equations with jumps
• Approximations of small jumps of Lévy processes with a view towards simulation
• The Euler Scheme for Feller Processes
• Backward stochastic differential equations and integral-partial differential equations
• Lévy Processes and Stochastic Calculus
• Universal approximation bounds for superpositions of a sigmoidal function
• Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
• Uniform error estimates for artificial neural network approximations for heat equations
• Deep ReLU networks and high-order finite element methods
• Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
• Deep hedging
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Deep optimal stopping