Malliavin Calculus for Score-based Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mirafzali, Ehsan, Gupta, Utkarsh, Wyrod, Patrick, Proske, Frank, Venturi, Daniele, Marinescu, Razvan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915633866735616
author Mirafzali, Ehsan
Gupta, Utkarsh
Wyrod, Patrick
Proske, Frank
Venturi, Daniele
Marinescu, Razvan
author_facet Mirafzali, Ehsan
Gupta, Utkarsh
Wyrod, Patrick
Proske, Frank
Venturi, Daniele
Marinescu, Razvan
contents We introduce a new framework based on Malliavin calculus to derive exact analytical expressions for the score function $\nabla \log p_t(x)$, i.e., the gradient of the log-density associated with the solution to stochastic differential equations (SDEs). Our approach combines classical integration-by-parts techniques with modern stochastic analysis tools, such as Bismut's formula and Malliavin calculus, and it works for both linear and nonlinear SDEs. In doing so, we establish a rigorous connection between the Malliavin derivative, its adjoint, the Malliavin divergence (Skorokhod integral), and diffusion generative models, thereby providing a systematic method for computing $\nabla \log p_t(x)$. In the linear case, we present a detailed analysis showing that our formula coincides with the analytical score function derived from the solution of the Fokker--Planck equation. For nonlinear SDEs with state-independent diffusion coefficients, we derive a closed-form expression for $\nabla \log p_t(x)$. We evaluate the proposed framework across multiple generative tasks and find that its performance is comparable to state-of-the-art methods. These results can be generalised to broader classes of SDEs, paving the way for new score-based diffusion generative models.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16917
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Malliavin Calculus for Score-based Diffusion Models
Mirafzali, Ehsan
Gupta, Utkarsh
Wyrod, Patrick
Proske, Frank
Venturi, Daniele
Marinescu, Razvan
Machine Learning
Probability
We introduce a new framework based on Malliavin calculus to derive exact analytical expressions for the score function $\nabla \log p_t(x)$, i.e., the gradient of the log-density associated with the solution to stochastic differential equations (SDEs). Our approach combines classical integration-by-parts techniques with modern stochastic analysis tools, such as Bismut's formula and Malliavin calculus, and it works for both linear and nonlinear SDEs. In doing so, we establish a rigorous connection between the Malliavin derivative, its adjoint, the Malliavin divergence (Skorokhod integral), and diffusion generative models, thereby providing a systematic method for computing $\nabla \log p_t(x)$. In the linear case, we present a detailed analysis showing that our formula coincides with the analytical score function derived from the solution of the Fokker--Planck equation. For nonlinear SDEs with state-independent diffusion coefficients, we derive a closed-form expression for $\nabla \log p_t(x)$. We evaluate the proposed framework across multiple generative tasks and find that its performance is comparable to state-of-the-art methods. These results can be generalised to broader classes of SDEs, paving the way for new score-based diffusion generative models.
title Malliavin Calculus for Score-based Diffusion Models
topic Machine Learning
Probability
url https://arxiv.org/abs/2503.16917