Polyak-Łojasiewicz inequality on the space of measures and convergence of mean-field birth-death processes

DOI10.1007/S00245-022-09962-0OpenAlexW4360980599MaRDI QIDQ2694477

Lukasz Szpruch, Mateusz B. Majka, Linshan Liu

Publication date: 3 April 2023

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.02774

zbMATH Keywords

exponential convergencebirth-death processesPolyak-Łojasiewicz conditionFisher-Rao gradient flowmean-field optimization

Mathematics Subject Classification ID

Probability measures on topological spaces (60B05) Branching processes (Galton-Watson, birth-and-death, etc.) (60J80)

Related Items (1)

Birth–death dynamics for sampling: global convergence, approximations and their asymptotics

Cites Work

• Unnamed Item
• Unnamed Item
• \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
• A family of functional inequalities: Łojasiewicz inequalities and displacement convex functions
• Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• Mean-field Langevin dynamics and energy landscape of neural networks
• Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
• A mean field view of the landscape of two-layer neural networks
• Probabilistic Theory of Mean Field Games with Applications I
• Measures, Integrals and Martingales
• A JKO Splitting Scheme for Kantorovich--Fisher--Rao Gradient Flows
• Optimal Transport

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