Polyak-\L ojasiewicz inequality on the space of measures and convergence of mean-field birth-death processes

DOI10.1007/S00245-022-09962-0MaRDI QIDQ6401281arXivFDO

Authors Linshan Liu, Mateusz B. Majka, Lukasz Szpruch

Publication date 6 June 2022

Mathematics Subject Classification ID

Variational problems in a geometric measure-theoretic setting (49Q20) Probability measures on topological spaces (60B05) Population dynamics (general) (92D25)

Abstract: The Polyak-Lojasiewicz inequality (PLI) in $mathbb{R}^d$ is a natural condition for proving convergence of gradient descent algorithms. In the present paper, we study an analogue of PLI on the space of probability measures $mathcalP(mathbb{R}^d)$ and show that it is a natural condition for showing exponential convergence of a class of birth-death processes related to certain mean-field optimization problems. We verify PLI for a broad class of such problems for energy functions regularised by the KL-divergence.

This page was built for publication: Polyak-\L ojasiewicz inequality on the space of measures and convergence of mean-field birth-death processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6401281)