Fokker-Planck equation driven by asymmetric Lévy motion
This work provides an efficient and principled numerical scheme for solving nonlocal Fokker-Planck equations with asymmetric Lévy noise, which is relevant for researchers in physics, finance, and biology modeling non-Gaussian processes.
The authors developed a fast numerical method for the Fokker-Planck equation driven by asymmetric Lévy motion, reducing computational complexity from O(J^2) to O(J log J) per time step while preserving the maximum principle. The method was validated against exact solutions and used to study the effects of stability index, skewness, and noise types on probability densities.
Non-Gaussian Lévy noises are present in many models for understanding underlining principles of physics, finance, biology and more. In this work, we consider the Fokker-Planck equation(FPE) due to one-dimensional asymmetric Lévy motion, which is a nonlocal partial differential equation. We present an accurate numerical quadrature for the singular integrals in the nonlocal FPE and develop a fast summation method to reduce the order of the complexity from $O(J^2)$ to $O(J\log J)$ in one time-step, where $J$ is the number of unknowns. We also provide conditions under which the numerical schemes satisfy maximum principle. Our numerical method is validated by comparing with exact solutions for special cases. We also discuss the properties of the probability density functions and the effects of various factors on the solutions, including the stability index, the skewness parameter, the drift term, the Gaussian and non-Gaussian noises and the domain size.