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: SIAM J. Math. Data Sci. (2020)
Keyphrases
- partial differential equations
- artificial neural networks
- generalization error
- numerical methods
- empirical risk minimization
- uniform convergence
- numerical solution
- model selection
- image denoising
- active learning
- pairwise
- learning algorithm
- neural network
- data sets
- cross validation
- image enhancement
- higher order
- objective function
- computer vision