Score-based Diffusion Models via Stochastic Differential Equations -- a Technical Tutorial
It serves as an expository resource for researchers and practitioners in machine learning, offering foundational insights for designing new models or algorithms, but it is incremental as it summarizes existing knowledge.
This article provides a technical tutorial on score-based diffusion models, focusing on their formulation via stochastic differential equations (SDEs) and covering key aspects like sampling and score matching, without presenting new experimental results or numerical outcomes.
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.