arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.01693cs.LGmath.PR
收藏

扩散模型的数学导论

A Mathematical Introduction to Diffusion Models

Duke University(杜克大学)

Jianfeng Lu

AI总结:

从采样视角出发,以证明为导向介绍扩散模型,涵盖经典采样动力学到现代扩散采样器、误差分析及推理时控制。

摘要:

这些笔记从采样视角给出了扩散模型的证明导向介绍,追踪从经典采样动力学到现代扩散采样器、它们的误差分析以及推理时控制的单一弧线。整体上,材料分层为:完整证明的核心定义和恒等式、在简化假设下证明的代表性估计、以及附带证明路线图的研究级定理。目标读者是具备概率背景但未接触过随机微分方程、随机数值或扩散模型的初级研究生。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑