Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Mo, Osher, Stanley, Li, Wuchen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.05723
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916880548102144
author Zhou, Mo
Osher, Stanley
Li, Wuchen
author_facet Zhou, Mo
Osher, Stanley
Li, Wuchen
contents The Fokker-Planck (FP) equation governs the evolution of densities for stochastic dynamics of physical systems, such as the Langevin dynamics and the Lorenz system. This work simulates FP equations through a mean field control (MFC) problem. We first formulate the FP equation as a continuity equation, where the velocity field consists of the drift function and the score function, i.e., the gradient of the logarithm of the density function. Next, we design a MFC problem that matches the velocity fields in a continuity equation with the ones in the FP equation. The score functions along deterministic trajectories are computed efficiently through the score-based normalizing flow, which only rely on the derivatives of the parameterized velocity fields. A convergence analysis is conducted for our algorithm on the FP equation of Ornstein-Uhlenbeck processes. Numerical results, including Langevin dynamics, underdamped Langevin dynamics, and various chaotic systems, validate the effectiveness of our proposed algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05723
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Simulating Fokker-Planck equations via mean field control of score-based normalizing flows
Zhou, Mo
Osher, Stanley
Li, Wuchen
Optimization and Control
34K35, 37N35, 58E25, 93C15, 93C20
G.1.7
The Fokker-Planck (FP) equation governs the evolution of densities for stochastic dynamics of physical systems, such as the Langevin dynamics and the Lorenz system. This work simulates FP equations through a mean field control (MFC) problem. We first formulate the FP equation as a continuity equation, where the velocity field consists of the drift function and the score function, i.e., the gradient of the logarithm of the density function. Next, we design a MFC problem that matches the velocity fields in a continuity equation with the ones in the FP equation. The score functions along deterministic trajectories are computed efficiently through the score-based normalizing flow, which only rely on the derivatives of the parameterized velocity fields. A convergence analysis is conducted for our algorithm on the FP equation of Ornstein-Uhlenbeck processes. Numerical results, including Langevin dynamics, underdamped Langevin dynamics, and various chaotic systems, validate the effectiveness of our proposed algorithms.
title Simulating Fokker-Planck equations via mean field control of score-based normalizing flows
topic Optimization and Control
34K35, 37N35, 58E25, 93C15, 93C20
G.1.7
url https://arxiv.org/abs/2506.05723