An analysis of the noise schedule for score-based generative models - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

An analysis of the noise schedule for score-based generative models

Résumé

Score-based generative models (SGMs) aim at estimating a target data distribution by learning score functions using only noise-perturbed samples from the target. Recent literature has focused extensively on assessing the error between the target and estimated distributions, gauging the generative quality through the Kullback-Leibler (KL) divergence and Wasserstein distances. All existing results have been obtained so far for time-homogeneous speed of the noise schedule. Under mild assumptions on the data distribution, we establish an upper bound for the KL divergence between the target and the estimated distributions, explicitly depending on any time-dependent noise schedule. Assuming that the score is Lipschitz continuous, we provide an improved error bound in Wasserstein distance, taking advantage of favourable underlying contraction mechanisms. We also propose an algorithm to automatically tune the noise schedule using the proposed upper bound. We illustrate empirically the performance of the noise schedule optimization in comparison to standard choices in the literature.
Fichier principal
Vignette du fichier
24-noisediff.pdf (799.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04441680 , version 1 (06-02-2024)

Identifiants

Citer

Stanislas Strasman, Antonio Ocello, Claire Boyer, Sylvain Le Corff, Vincent Lemaire. An analysis of the noise schedule for score-based generative models. 2024. ⟨hal-04441680⟩
47 Consultations
28 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More