A PDE Perspective on Generative Diffusion Models

Kang Liu; Enrique Zuazua

math.OCNov 8, 2025

A PDE Perspective on Generative Diffusion Models

Authors: Kang Liu, Enrique Zuazua

Organizations: Universit´e Bourgogne Europe, CNRS, Institut de Mathematiques de Bourgogne, 21000 Dijon, France. · Friedrich - Alexander - Universität Erlangen - Nürnberg, Department of Mathematics, Chair for Dynamics, Control, Machine Learning, and Numerics (Alexander von Humboldt Professorship), 91058 Erlangen, Germany. · Universidad Aut´onoma de Madrid, Departamento de Matem´aticas, 28049 Madrid, Spain. · Chair of Computational Mathematics, Fundaci´on Deusto, 48007 Bilbao, Basque Country, Spain.

Abstract

Score-based diffusion models have emerged as a powerful class of generative methods, with successful applications across diverse domains. Despite their empirical success, their mathematical foundations remain only partially understood, particularly regarding the stability and consistency of the stochastic and partial differential equations underlying their dynamics. In this work, we develop a partial differential equation (PDE) framework for score-based diffusion processes associated with the heat flow of a compactly supported data measure. After establishing weak well-posedness on positive-time intervals, we derive a sharp one-sided divergence bound for the score and use it to obtain sharp uniform $L^p$ -stability estimates for the generative Fokker--Planck equation. This bound is the Euclidean form of the Li--Yau differential inequality. Through entropy stability methods, we prove that the generated laws converge in the $2$ -Wasserstein distance at rate $\sqrt t$ as $t\to0^+$ to a probability measure supported on the data support. This holds for both deterministic and stochastic generation, for positive terminal densities with finite absolute entropy and second moment. In the deterministic case, almost every trajectory converges to a point of the data support; for empirical data, we further obtain a trajectory-wise square-root rate. These results clarify how exact-score dynamics concentrate on the data support without necessarily recovering the data distribution. An explicitly solvable case identifies the limiting weights and their dependence on Gaussian initialization, while a relative-entropy estimate quantifies the effect of score approximation. Together, these findings connect the stability and concentration mechanisms with score learning and early stopping, providing a mathematical perspective on the balance between imitation fidelity and generative diversity.

Figures & tables

Figure 1. Score function (left) and log-density (right) of the heat flow originating from $u_{0}=0.7\delta_{-5}+0.2\delta_{0}+0.1\delta_{5}$ , shown at $t=0.01,0.1,1$ . The steep negative score slopes near the atoms illustrate the $1/t$ scale in the Li–Yau estimate. The log-density and score are evaluated using log-sum-exp and normalized Gaussian weights, respectively.

Panel of Figure 2 — Figure 2. Score-based generation on the lemniscate dataset: comparison between the true ((A)-(B)) and empirical scores ((C)-(D)), and the effect of the choice of the stopping time $t_{\min}\in\{0.1,\,0.01,\,0.001\}$ . The true score ((A)-(B)) corresponds to the solution of the heat equation, given by the convolution with the Gaussian heat kernel, computed by means of numerical quadrature, while the empirical score ((C)-(D)) is obtained from a finite sample of data points via the explicit expression ( 3.8 ). In all experiments, we set the backward diffusion parameter to be $\epsilon=0.2$ . The displayed sample region encompasses $95\%$ of the $10{,}000$ reverse-time samples, reducing the effect of extreme stochastic trajectories.

Figure 3. Trajectories of the score-based ODE ( $\epsilon=0$ ) with $u_{0}=\tfrac{1}{2}\big(\delta_{(-1,0)}+\delta_{(1,0)}\big)$ . Initial points with $x<0$ converge to $(-1,0)$ , those with $x>0$ converge to $(1,0)$ , and points with $x=0$ converge to the barycenter $(0,0)$ .

Panel of Figure 4 — Figure 4. Voronoi diagram and $\gamma$ –Voronoi cores for five points in $\mathbb{R}^{2}$ . When $\gamma=0$ , we recover the classical Voronoi diagram.

Explore similar work

A Hyperfinite Framework for Score-Based Generative Modeling
Aug 3, 2026Sunder Ram KrishnanScore Matching Stochastic Differential Equations
Kerala School of Mathematics, Kozhikode 673571, Kerala, India.
The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
Jun 13, 2025Bernardo P. Schaeffer, Ricardo M. S. Rosa, Glauco ValleStochastic Differential Equations Diffusion Sampling
Instituto de Matem´atica, Universidade Federal do Rio de Janeiro
Probability flow ODEs in score-based and reflected diffusion models
Oct 2, 2026Rama CONTDiffusion Sampling Diffusion Models
Mathematical Institute, University of Oxford

Aug 3, 2026J/K move · Enter open · S save

A Hyperfinite Framework for Score-Based Generative Modeling

Sunder Ram Krishnan

Kerala School of Mathematics, Kozhikode 673571, Kerala, India.

Score Matching Stochastic Differential Equations Score-Based Generative Modeling

Open paper AskPDF arXiv

Score-based diffusion models are typically formulated using continuous-time stochastic differential equations and measure-theoretic stochastic calculus. In this paper, we develop a hyperfinite formulation of score-based generative modeling within the framework of Nonstandard Analysis. Starting from an internal diffusion process on a hyperfinite grid, we derive the associated infinitesimal generator and establish its correspondence with the classical Fokker--Planck equation. We then obtain a hyperfinite backward-mean identity that yields the reverse-time drift and provides a constructive derivation of the reverse-time SDE. Building on these results, we show that minimization of an internal score-matching objective recovers the score function required by the reverse-time dynamics, thereby connecting score estimation with generative sampling directly at the hyperfinite level. Under suitable assumptions, we further derive a hyperfinite Girsanov formula and establish a relationship between likelihood optimization and Fisher-divergence objectives. Finally, we analyze the second-order consistency of the hyperfinite dynamics and show that the leading correction term depends explicitly on the fourth moment of the increment distribution, with the Gaussian value

κ=3

eliminating the leading dispersion contribution. Taken together, these results provide a unified hyperfinite framework for diffusion-based generative modeling--while laying foundations for further extensions--that links discrete grid dynamics, reverse-time diffusion, score matching, and likelihood-based formulations within a common nonstandard setting.

Abstract

Explore similar work

A Hyperfinite Framework for Score-Based Generative Modeling

The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis

Probability flow ODEs in score-based and reflected diffusion models