Score-based diffusion models via stochastic differential equations
Statistics Surveys · 01.01.2025 · 19 (none) · 28-64
DOI: 10.1214/25-ss152 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistics Surveys, erschienen am 01.01.2025. Verfasst von Wenpin Tang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 103 Literaturangaben.
Abstract (Originalsprache)
This is an expository article on the score-based diffusion models, with a particular focus on the formulation via stochastic differential equations (SDE). After a gentle introduction, we discuss the two pillars in the diffusion modeling – sampling and score matching, which encompass the SDE/ODE sampling, score matching efficiency, the consistency models, and reinforcement learning. Short proofs are given to illustrate the main idea of the stated results. The article is primarily a technical introduction to the field, and practitioners may also find some analysis useful in designing new models or algorithms.
Zitieren
APA
Tang, W., & Zhao, H. (2025). Score-based diffusion models via stochastic differential equations. Statistics Surveys, 19(none), 28-64. https://doi.org/10.1214/25-ss152
Vancouver
Tang W, Zhao H. Score-based diffusion models via stochastic differential equations. Statistics Surveys. 2025;19(none):28-64. doi:10.1214/25-ss152
BibTeX
@article{Tang2025,
author = {Tang, Wenpin and Zhao, Hanyang},
title = {Score-based diffusion models via stochastic differential equations},
journal = {Statistics Surveys},
year = {2025},
volume = {19},
number = {none},
pages = {28--64},
doi = {10.1214/25-ss152}
}
EUVIMED