A Mathematical Introduction to Diffusion Models
It serves as an educational resource for students new to diffusion models, but offers no novel research contributions.
This paper provides a mathematical introduction to diffusion models, covering sampling dynamics, error analysis, and inference-time control, aimed at beginning graduate students.
These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics to modern diffusion samplers, their error analysis, and inference-time control. Throughout, the material is layered into core definitions and identities proved in full, representative estimates proved under simplifying assumptions, and research-level theorems stated with a proof roadmap. The intended audience is beginning graduate students with a background in probability but no prior exposure to stochastic differential equations, stochastic numerics, or diffusion models.