Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities
This provides a theoretical foundation for Fisher-Rao gradient flows, enabling uniform convergence in Bayesian inference without restrictive assumptions, though it is incremental relative to existing Wasserstein-based methods.
The paper tackles the analysis of gradient flows under the Fisher-Rao metric for probability densities, establishing functional inequalities and geodesic convexity without relying on log-concavity or log-Sobolev constants, resulting in uniform convergence rates across general target distributions for applications like Bayesian posterior sampling.
The dynamics of probability density functions has been extensively studied in science and engineering to understand physical phenomena and facilitate algorithmic design. Of particular interest are dynamics that can be formulated as gradient flows of energy functionals under the Wasserstein metric. The development of functional inequalities, such as the log-Sobolev inequality, plays a pivotal role in analyzing the convergence of these dynamics. The goal of this paper is to parallel the success of techniques using functional inequalities, for dynamics that are gradient flows under the Fisher-Rao metric, with various $f$-divergences as energy functionals. Such dynamics take the form of a nonlocal differential equation, for which existing analysis critically relies on using the explicit solution formula in special cases. We provide a comprehensive study on functional inequalities and the relevant geodesic convexity for Fisher-Rao gradient flows under minimal assumptions. A notable feature of the obtained functional inequalities is that they do not depend on the log-concavity or log-Sobolev constants of the target distribution. Consequently, the convergence rate of the dynamics (assuming well-posed) is uniform across general target distributions, making them potentially desirable dynamics for posterior sampling applications in Bayesian inference.