Hellinger-Kantorovich Gradient Flows: Global Exponential Decay of Entropy Functionals

TL;DR

This paper provides a comprehensive analysis of gradient flows in the Hellinger-Kantorovich geometry, establishing conditions for exponential decay of entropy functionals and developing new analytical tools for positive measures.

Contribution

It offers a complete characterization of entropy decay in HK gradient flows, including novel shape-mass decomposition techniques for positive measures.

Findings

Proves exponential decay of entropy functionals in HK gradient flows.

Develops shape-mass decomposition for positive measures.

Extends classical dissipation estimates to HK geometry.

Abstract

We investigate a family of gradient flows of positive and probability measures, focusing on the Hellinger-Kantorovich (HK) geometry, which unifies transport mechanism of Otto-Wasserstein, and the birth-death mechanism of Hellinger (or Fisher-Rao). A central contribution is a complete characterization of global exponential decay behaviors of entropy functionals (e.g. KL, $\chi^2$) under Otto-Wasserstein and Hellinger-type gradient flows. In particular, for the more challenging analysis of HK gradient flows on positive measures -- where the typical log-Sobolev arguments fail -- we develop a specialized shape-mass decomposition that enables new analysis results. Our approach also leverages the (Polyak-)\L{}ojasiewicz-type functional inequalities and a careful extension of classical dissipation estimates. These findings provide a unified and complete theoretical framework for gradient flows and underpin applications in computational algorithms for statistical inference, optimization, and machine learning.