Adaptive deep density approximation for Fokker-Planck equations
This work addresses computational challenges in high-dimensional probability density estimation for physics and engineering applications, representing an incremental improvement with a novel adaptive sampling method.
The paper tackles solving high-dimensional steady-state Fokker-Planck equations on unbounded domains by proposing ADDA-KR, an adaptive deep density approximation strategy using a flow-based generative model called KRnet, which shows weaker dimensionality dependence and efficient estimation of high-dimensional densities in numerical experiments.
In this paper we present an adaptive deep density approximation strategy based on KRnet (ADDA-KR) for solving the steady-state Fokker-Planck (F-P) equations. F-P equations are usually high-dimensional and defined on an unbounded domain, which limits the application of traditional grid based numerical methods. With the Knothe-Rosenblatt rearrangement, our newly proposed flow-based generative model, called KRnet, provides a family of probability density functions to serve as effective solution candidates for the Fokker-Planck equations, which has a weaker dependence on dimensionality than traditional computational approaches and can efficiently estimate general high-dimensional density functions. To obtain effective stochastic collocation points for the approximation of the F-P equation, we develop an adaptive sampling procedure, where samples are generated iteratively using the approximate density function at each iteration. We present a general framework of ADDA-KR, validate its accuracy and demonstrate its efficiency with numerical experiments.