Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations.
Christian BeckWeinan EArnulf JentzenPublished in: CoRR (2017)
Keyphrases
- approximation algorithms
- stochastic differential equations
- machine learning
- high dimensional
- maximum a posteriori estimation
- nonlinear partial differential equations
- brownian motion
- np hard
- special case
- additive gaussian noise
- fractional brownian motion
- constant factor
- higher order
- partial differential equations
- stochastic process
- worst case
- learning algorithm
- long range
- learning problems
- differential equations
- diffusion process
- kernel methods
- non stationary
- denoising
- feature space
- optimal solution