Weak Adversarial Neural Pushforward Method for the McKean-Vlasov / Mean-Field Fokker-Planck Equation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Andrew Qing, Cai, Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914414214512640
author He, Andrew Qing
Cai, Wei
author_facet He, Andrew Qing
Cai, Wei
contents We extend the Weak Adversarial Neural Pushforward Method (WANPM) to the McKean--Vlasov mean-field Fokker--Planck equation, covering both the stationary and time-dependent cases. The key observation is that the mean-field nonlinearity -- an expectation under the solution distribution -- is naturally estimated by Monte Carlo sampling from the pushforward network, requiring no change to the architecture and only minor modifications to the training loop. For the quadratic (granular media) interaction kernel, the interaction term reduces to the batch sample mean, eliminating secondary sampling entirely. We also identify a dimension-dependent frequency initialization rule for the adversarial test functions, necessary to avoid spurious minimizers. Numerical experiments on linear McKean--Vlasov benchmarks in 2, 5, 20, and 100 dimensions confirm accurate recovery of the exact Gaussian stationary and transient distributions, with training times ranging from 27 seconds (2D) to 10 minutes (100D) on a single GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16186
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Weak Adversarial Neural Pushforward Method for the McKean-Vlasov / Mean-Field Fokker-Planck Equation
He, Andrew Qing
Cai, Wei
Numerical Analysis
65N75, 68T07, 35Q84, 60K35
We extend the Weak Adversarial Neural Pushforward Method (WANPM) to the McKean--Vlasov mean-field Fokker--Planck equation, covering both the stationary and time-dependent cases. The key observation is that the mean-field nonlinearity -- an expectation under the solution distribution -- is naturally estimated by Monte Carlo sampling from the pushforward network, requiring no change to the architecture and only minor modifications to the training loop. For the quadratic (granular media) interaction kernel, the interaction term reduces to the batch sample mean, eliminating secondary sampling entirely. We also identify a dimension-dependent frequency initialization rule for the adversarial test functions, necessary to avoid spurious minimizers. Numerical experiments on linear McKean--Vlasov benchmarks in 2, 5, 20, and 100 dimensions confirm accurate recovery of the exact Gaussian stationary and transient distributions, with training times ranging from 27 seconds (2D) to 10 minutes (100D) on a single GPU.
title Weak Adversarial Neural Pushforward Method for the McKean-Vlasov / Mean-Field Fokker-Planck Equation
topic Numerical Analysis
65N75, 68T07, 35Q84, 60K35
url https://arxiv.org/abs/2603.16186