Saved in:
Bibliographic Details
Main Authors: Niemann, Onno, Muñoz, Gonzalo Martínez, Gonzalez, Alberto Suárez
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.15171
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911598885470208
author Niemann, Onno
Muñoz, Gonzalo Martínez
Gonzalez, Alberto Suárez
author_facet Niemann, Onno
Muñoz, Gonzalo Martínez
Gonzalez, Alberto Suárez
contents Recent work has shown that diffusion models trained with the denoising score matching (DSM) objective often violate the Fokker--Planck (FP) equation that governs the evolution of the true data density. Directly penalizing these deviations in the objective function reduces their magnitude but introduces a significant computational overhead. It is also observed that enforcing strict adherence to the FP equation does not necessarily lead to improvements in the quality of the generated samples, as often the best results are obtained with weaker FP regularization. In this paper, we investigate whether simpler penalty terms can provide similar benefits. We empirically analyze several lightweight regularizers, study their effect on FP residuals and generation quality, and show that the benefits of FP regularization are available at substantially lower computational cost. Our code is available at https://github.com/OnnoNiemann/fp_diffusion_analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15171
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation
Niemann, Onno
Muñoz, Gonzalo Martínez
Gonzalez, Alberto Suárez
Computer Vision and Pattern Recognition
Machine Learning
Recent work has shown that diffusion models trained with the denoising score matching (DSM) objective often violate the Fokker--Planck (FP) equation that governs the evolution of the true data density. Directly penalizing these deviations in the objective function reduces their magnitude but introduces a significant computational overhead. It is also observed that enforcing strict adherence to the FP equation does not necessarily lead to improvements in the quality of the generated samples, as often the best results are obtained with weaker FP regularization. In this paper, we investigate whether simpler penalty terms can provide similar benefits. We empirically analyze several lightweight regularizers, study their effect on FP residuals and generation quality, and show that the benefits of FP regularization are available at substantially lower computational cost. Our code is available at https://github.com/OnnoNiemann/fp_diffusion_analysis.
title An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.15171