Saved in:
Bibliographic Details
Main Authors: Jiao, Yuling, Kang, Lican, Lin, Huazhen, Liu, Jin, Zuo, Heng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.13309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929642925981696
author Jiao, Yuling
Kang, Lican
Lin, Huazhen
Liu, Jin
Zuo, Heng
author_facet Jiao, Yuling
Kang, Lican
Lin, Huazhen
Liu, Jin
Zuo, Heng
contents This paper aims to conduct a comprehensive theoretical analysis of current diffusion models. We introduce a novel generative learning methodology utilizing the Schr{ö}dinger bridge diffusion model in latent space as the framework for theoretical exploration in this domain. Our approach commences with the pre-training of an encoder-decoder architecture using data originating from a distribution that may diverge from the target distribution, thus facilitating the accommodation of a large sample size through the utilization of pre-existing large-scale models. Subsequently, we develop a diffusion model within the latent space utilizing the Schr{ö}dinger bridge framework. Our theoretical analysis encompasses the establishment of end-to-end error analysis for learning distributions via the latent Schr{ö}dinger bridge diffusion model. Specifically, we control the second-order Wasserstein distance between the generated distribution and the target distribution. Furthermore, our obtained convergence rates effectively mitigate the curse of dimensionality, offering robust theoretical support for prevailing diffusion models.
format Preprint
id arxiv_https___arxiv_org_abs_2404_13309
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Latent Schr{ö}dinger Bridge Diffusion Model for Generative Learning
Jiao, Yuling
Kang, Lican
Lin, Huazhen
Liu, Jin
Zuo, Heng
Machine Learning
This paper aims to conduct a comprehensive theoretical analysis of current diffusion models. We introduce a novel generative learning methodology utilizing the Schr{ö}dinger bridge diffusion model in latent space as the framework for theoretical exploration in this domain. Our approach commences with the pre-training of an encoder-decoder architecture using data originating from a distribution that may diverge from the target distribution, thus facilitating the accommodation of a large sample size through the utilization of pre-existing large-scale models. Subsequently, we develop a diffusion model within the latent space utilizing the Schr{ö}dinger bridge framework. Our theoretical analysis encompasses the establishment of end-to-end error analysis for learning distributions via the latent Schr{ö}dinger bridge diffusion model. Specifically, we control the second-order Wasserstein distance between the generated distribution and the target distribution. Furthermore, our obtained convergence rates effectively mitigate the curse of dimensionality, offering robust theoretical support for prevailing diffusion models.
title Latent Schr{ö}dinger Bridge Diffusion Model for Generative Learning
topic Machine Learning
url https://arxiv.org/abs/2404.13309