Random feature neural networks learn Black-Scholes type PDEs without curse of dimensionality
arXiv:2106.08900
Abstract
This article investigates the use of random feature neural networks for learning Kolmogorov partial (integro-)differential equations associated to Black-Scholes and more general exponential Lévy models. Random feature neural networks are single-hidden-layer feedforward neural networks in which only the output weights are trainable. This makes training particularly simple, but (a priori) reduces expressivity. Interestingly, this is not the case for Black-Scholes type PDEs, as we show here. We derive bounds for the prediction error of random neural networks for learning sufficiently non-degenerate Black-Scholes type models. A full error analysis is provided and it is shown that the derived bounds do not suffer from the curse of dimensionality. We also investigate an application of these results to basket options and validate the bounds numerically. These results prove that neural networks are able to \textit{learn} solutions to Black-Scholes type PDEs without the curse of dimensionality. In addition, this provides an example of a relevant learning problem in which random feature neural networks are provably efficient.
References in corpus (15)
- Solving high-dimensional partial differential equations using deep learning
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes
- The generalization error of random features regression: Precise asymptotics and double descent curve
- Generalization Properties of Learning with Random Features
- A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- The Modern Mathematics of Deep Learning
- A Priori Estimates of the Population Risk for Two-layer Neural Networks
- An overview on deep learning-based approximation methods for partial differential equations
- Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't
- Approximation and Estimation for High-Dimensional Deep Learning Networks
- Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
- Learning with SGD and Random Features
- On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics
- Neural networks-based algorithms for stochastic control and PDEs in finance