An analysis of the noise schedule for score-based generative models - Centre de mathématiques appliquées (CMAP) Access content directly
Preprints, Working Papers, ... Year : 2024

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

Abstract

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. 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. Under additional regularity assumptions, taking advantage of favorable underlying contraction mechanisms, we provide a tighter error bound in Wasserstein distance compared to state-of-the-art results. In addition to being tractable, this upper bound jointly incorporates properties of the target distribution and SGM hyperparameters that need to be tuned during training.
Fichier principal
Vignette du fichier
24-noise_diff_hal.pdf (1.04 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04441680 , version 1 (06-02-2024)
hal-04441680 , version 2 (23-05-2024)

Identifiers

Cite

Stanislas Strasman, Antonio Ocello, Claire Boyer, Sylvain Le Corff, Vincent Lemaire. An analysis of the noise schedule for score-based generative models. 2024. ⟨hal-04441680v2⟩
121 View
105 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More