Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities
Top Cited Papers
- 12 March 2026
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Mathematical Analysis
- Vol. 58 (2) , 1062-1099
Abstract
The dynamics of probability density functions have been extensively studied in computational science and engineering to understand physical phenomena and facilitate algorithmic design. Of particular interest are dynamics 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. This paper aims to extend the success of functional inequality techniques to dynamics that are gradient flows under the Fisher–Rao metric, with various [Formula: see text]-divergences serving as energy functionals. Such dynamics take the form of nonlocal differential equations, for which existing analyses critically rely on explicit solution formulas in special cases. We provide a comprehensive study of functional inequalities and the relevant geodesic convexity for Fisher–Rao gradient flows under minimal assumptions. A notable feature of our functional inequalities is their independence from the log-concavity or log-Sobolev constants of the target distribution. Consequently, the convergence rate of the dynamics (assuming well-posedness) remains uniform across general target distributions.Keywords
All Related Versions
Funding Information
- Maria de Maeztu Excellence Unit IMAG (CEX2020-001105-M)
- H2020 European Research Council (883363)
- Fundamental Research Funds for the Central Universities
- Courant Institute of Mathematical Sciences, New York University
- National Natural Science Foundation of China (12471403)
- Engineering and Physical Sciences Research Council (EP/T022132/1)
- Engineering and Physical Sciences Research Council (EP/V051121/1)
This publication has 73 references indexed in Scilit:
- Bayesian calibration for large‐scale fluid structure interaction problems under embedded/immersed boundary frameworkInternational Journal for Numerical Methods in Engineering, 2022
- Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High‐Resolution SimulationsGeophysical Research Letters, 2017
- Optimal Transport for Applied Mathematicians2015
- Analysis and Geometry of Markov Diffusion Operators2014
- Stochastic Processes and Applications2014
- Bayesian Methods for Structural Dynamics and Civil Engineering2010
- Transport inequalities, gradient estimates, entropy and Ricci curvatureCommunications on Pure and Applied Mathematics, 2004
- Generalization of an Inequality by Talagrand and Links with the Logarithmic Sobolev InequalityJournal of Functional Analysis, 2000
- A Convexity Principle for Interacting GasesAdvances in Mathematics, 1997
- Die Fisher‐Information und symplektische StrukturenMathematische Nachrichten, 1991