To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models

Autor:	Vargas, Francisco, Reu, Teodora, Kerekes, Anna, Bronstein, Michael M
Rok vydání:	2023
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transforms the data distribution into a Gaussian. Samples from the generative model are then obtained by simulating an approximation of the time reversal of this diffusion initialized by Gaussian samples. Recent research has explored adapting diffusion models for sampling and inference tasks. In this paper, we leverage known connections to stochastic control akin to the F\"ollmer drift to extend established neural network approximation results for the F\"ollmer drift to denoising diffusion models and samplers. Comment: arXiv admin note: text overlap with arXiv:1903.01608 by other authors
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.09605 Zobrazit plný text záznamu View this record from Arxiv