Journals
Resources
About Us
Open Access

Mathematical Analysis of Singularities in the Diffusion Model Under the Submanifold Assumption

Mathematical Analysis of Singularities in the Diffusion Model Under the Submanifold Assumption

Year:    2025

Author:    Yubin Lu, Zhongjian Wang, Guillaume Bal

East Asian Journal on Applied Mathematics, Vol. 15 (2025), Iss. 4 : pp. 669–700

Abstract

This paper concerns the mathematical analyses of the diffusion model in machine learning. The drift term of the backward sampling process is represented as a conditional expectation involving the data distribution and the forward diffusion. The training process aims to find such a drift function by minimizing the mean-squared residue related to the conditional expectation. Using small-time approximations of the Green’s function of the forward diffusion, we show that the analytical mean drift function in DDPM and the score function in SGM asymptotically blow up in the final stages of the sampling process for singular data distributions such as those concentrated on lower-dimensional manifolds, and are therefore difficult to approximate by a network. To overcome this difficulty, we derive a new target function and associated loss, which remains bounded even for singular data distributions. We validate the theoretical findings with several numerical examples.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/eajam.2024-158.280924

East Asian Journal on Applied Mathematics, Vol. 15 (2025), Iss. 4 : pp. 669–700

Published online:    2025-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    32

Keywords:    Generative model singularities Green’s kernel adaptive time-stepping low-dimensional manifold.

Author Details

Yubin Lu

Zhongjian Wang

Guillaume Bal