Learning Stochastic Differential Equations With Gaussian Processes Without Gradient Matching
We introduce a novel paradigm for learning non-parametric drift and diffusion functions for stochastic differential equation (SDE) that are learnt to simulate trajectory distributions that match observations of arbitrary spacings. This is in contrast to existing gradient matching or other approximations that do not optimize simulated responses. We demonstrate that our general stochastic distribution optimisation leads to robust and efficient learning of SDE systems.
READ FULL TEXT