Neural Parametric Fokker-Planck Equations

Abstract

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. We call such ODEs neural parametric Fokker-Planck equations. The fact that the Fokker-Planck equation can be viewed as the $L^2$-Wasserstein gradient flow of Kullback-Leibler (KL) divergence allows us to derive the ODEs as the constrained $L^2$-Wasserstein gradient flow of KL divergence on the set of probability densities generated by neural networks. For numerical computation, we design a variational semi-implicit scheme for the time discretization of the proposed ODE. Such an algorithm is sampling-based, which can readily handle the Fokker-Planck equations in higher dimensional spaces. Moreover, we also establish bounds for the asymptotic convergence analysis of the neural parametric Fokker-Planck equation as well as the error analysis for both the continuous and discrete versions. Several numerical examples are provided to illustrate the performance of the proposed algorithms and analysis.

References in corpus (10)

• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Nonlinear Approximation and (Deep) ReLU Networks
• Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimation
• Primal dual methods for Wasserstein gradient flows
• Ricci curvature for parametric statistics via optimal transport
• The data-driven Schroedinger bridge
• Parametric Fokker-Planck equation

Cited by in corpus (2)

• Integrating Dynamical Systems Modeling with Spatiotemporal scRNA-seq Data Analysis
• Parameterized Wasserstein Gradient Flow