A uniform-in-time nonlocal approximation of the standard Fokker-Planck equation

TL;DR

This paper introduces a nonlocal approximation to the Fokker-Planck equation that provides uniform-in-time convergence estimates to equilibrium, linking probabilistic methods with PDE analysis.

Contribution

It develops a novel nonlocal approximation of the Fokker-Planck equation with uniform convergence estimates, using Harris's theorem and probabilistic techniques.

Findings

Proves uniform convergence of the approximation to the Fokker-Planck solution over time.

Establishes equilibrium tail and regularity properties for the approximation.

Links the approximation's convergence to probabilistic central limit theorem results.

Abstract

We study a nonlocal approximation of the Fokker-Planck equation in which we can estimate the speed of convergence to equilibrium in a way which does not degenerate as we approach the local limit of the equation. This uniform estimate cannot be easily obtained with standard inequalities or entropy methods, but can be obtained through the use of Harris's theorem, finding interesting links to quantitative versions of the central limit theorem in probability. As a consequence one can prove that solutions of this nonlocal approximation converge to solutions of the usual Fokker-Planck equation uniformly in time-hence we show the approximation is asymptotic-preserving in this sense. The associated equilibrium has some interesting tail and regularity properties, which we also study.