Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Mo, Osher, Stanley, Li, Wuchen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916588470403072
author Zhou, Mo
Osher, Stanley
Li, Wuchen
author_facet Zhou, Mo
Osher, Stanley
Li, Wuchen
contents Classical neural ordinary differential equations (ODEs) are powerful tools for approximating the log-density functions in high-dimensional spaces along trajectories, where neural networks parameterize the velocity fields. This paper proposes a system of neural differential equations representing first- and second-order score functions along trajectories based on deep neural networks. We reformulate the mean field control (MFC) problem with individual noises into an unconstrained optimization problem framed by the proposed neural ODE system. Additionally, we introduce a novel regularization term to enforce characteristics of viscous Hamilton--Jacobi--Bellman (HJB) equations to be satisfied based on the evolution of the second-order score function. Examples include regularized Wasserstein proximal operators (RWPOs), probability flow matching of Fokker--Planck (FP) equations, and linear quadratic (LQ) MFC problems, which demonstrate the effectiveness and accuracy of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16471
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems
Zhou, Mo
Osher, Stanley
Li, Wuchen
Optimization and Control
Machine Learning
34H05
G.1.7
Classical neural ordinary differential equations (ODEs) are powerful tools for approximating the log-density functions in high-dimensional spaces along trajectories, where neural networks parameterize the velocity fields. This paper proposes a system of neural differential equations representing first- and second-order score functions along trajectories based on deep neural networks. We reformulate the mean field control (MFC) problem with individual noises into an unconstrained optimization problem framed by the proposed neural ODE system. Additionally, we introduce a novel regularization term to enforce characteristics of viscous Hamilton--Jacobi--Bellman (HJB) equations to be satisfied based on the evolution of the second-order score function. Examples include regularized Wasserstein proximal operators (RWPOs), probability flow matching of Fokker--Planck (FP) equations, and linear quadratic (LQ) MFC problems, which demonstrate the effectiveness and accuracy of the proposed method.
title Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems
topic Optimization and Control
Machine Learning
34H05
G.1.7
url https://arxiv.org/abs/2409.16471