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.
Julius BernerPhilipp GrohsArnulf JentzenPublished in: CoRR (2018)
Keyphrases
- partial differential equations
- generalization error
- artificial neural networks
- numerical methods
- empirical risk minimization
- training set
- neural network
- image denoising
- uniform convergence
- numerical solution
- image processing
- real valued
- cross validation
- model selection
- differential equations
- image enhancement
- worst case