Regularity of the score function in generative models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Stéphanovitch, Arthur
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918069160378368
author Stéphanovitch, Arthur
author_facet Stéphanovitch, Arthur
contents We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support convergence and stability analyses in both diffusion and ODE-based generative models. In addition, we derive higher-order regularity bounds, which simplify existing arguments for optimally approximating the score function using neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Regularity of the score function in generative models
Stéphanovitch, Arthur
Statistics Theory
We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support convergence and stability analyses in both diffusion and ODE-based generative models. In addition, we derive higher-order regularity bounds, which simplify existing arguments for optimally approximating the score function using neural networks.
title Regularity of the score function in generative models
topic Statistics Theory
url https://arxiv.org/abs/2506.19559