Machine Learning Approximation Algorithms for High-Dimensional Fully Nonlinear Partial Differential Equations and Second-order Backward Stochastic Differential Equations.
Christian BeckWeinan EArnulf JentzenPublished in: J. Nonlinear Sci. (2019)
Keyphrases
- approximation algorithms
- stochastic differential equations
- machine learning
- high dimensional
- maximum a posteriori estimation
- nonlinear partial differential equations
- brownian motion
- np hard
- special case
- worst case
- fractional brownian motion
- additive gaussian noise
- higher order
- constant factor
- differential equations
- optimal control
- learning algorithm
- stochastic process
- partial differential equations
- high order
- feature space
- diffusion process
- kernel methods
- non stationary
- multiresolution
- computer vision