Non-Parametric Learning of Stochastic Differential Equations with Fast Rates of Convergence

05/24/2023
by   Riccardo Bonalli, et al.
0

We propose a novel non-parametric learning paradigm for the identification of drift and diffusion coefficients of non-linear stochastic differential equations, which relies upon discrete-time observations of the state. The key idea essentially consists of fitting a RKHS-based approximation of the corresponding Fokker-Planck equation to such observations, yielding theoretical estimates of learning rates which, unlike previous works, become increasingly tighter when the regularity of the unknown drift and diffusion coefficients becomes higher. Our method being kernel-based, offline pre-processing may in principle be profitably leveraged to enable efficient numerical implementation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset