Large-scale concentration and relaxation for mean-field Langevin particle systems
read the original abstract
We study the Langevin dynamics of diffusive particles with regular pairwise interactions under mean-field scaling. By approximating empirical distributions with conditional distributions, we establish coercive and contractive properties for the modulated free energy functional. These properties yield near-optimal large-scale concentration and relaxation rates for the particle system throughout the subcritical regime. Furthermore, we derive generation of chaos estimates with the optimal order of particle approximation. As a simpler instance, we demonstrate long-time convergence of the independent projection of Langevin dynamics.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Nesterov acceleration for the Wasserstein minimization of displacement-convex free energies
Mean-field underdamped Langevin dynamics achieve Nesterov acceleration for Wasserstein gradient flows of displacement-convex free energies.
-
Nesterov acceleration for the Wasserstein minimization of displacement-convex free energies
Mean-field underdamped Langevin dynamics achieves sqrt(PL constant) convergence for Wasserstein minimization of displacement-convex free energies, improving on standard gradient flow rates via a diffusive-to-ballistic...
-
Nesterov acceleration for the Wasserstein minimization of displacement-convex free energies
Mean-field underdamped Langevin dynamics achieves Nesterov acceleration for Wasserstein minimization of displacement-convex free energies via sqrt(PL) convergence rates.
-
Nesterov acceleration for the Wasserstein minimization of displacement-convex free energies
Mean-field underdamped Langevin dynamics achieves Nesterov acceleration for Wasserstein minimization of displacement-convex free energies by extending a linear-case result to the nonlinear setting.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.