Neural Parametric Fokker-Planck Equations

15 Jun 2020 Liu Shu Li Wuchen Zha Hongyuan Zhou Haomin

In this paper, we develop and analyze numerical methods for high dimensional Fokker-Planck equations by leveraging generative models from deep learning. Our starting point is a formulation of the Fokker-Planck equation as a system of ordinary differential equations (ODEs) on finite-dimensional parameter space with the parameters inherited from generative models such as normalizing flows... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Categories


  • NUMERICAL ANALYSIS
  • NUMERICAL ANALYSIS