按年被提到
20232023 · 2 次2026
视觉、语音与图像生成›扩散模型·arXiv:2310.17467 · stat.ML

The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability

Luca Ambrogioni · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-10-30 · 最近 2023-11-13
2不同的人
2活跃月份
2讨论串
17被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Generative diffusion models have achieved spectacular performance in many areas of machine learning and generative modeling. While the fundamental ideas behind these models come from non-equilibrium physics, variational inference and stochastic calculus, in this paper we show that many aspects of these models can be understood using the tools of equilibrium statistical mechanics. Using this reformulation, we show that generative diffusion models undergo second-order phase transitions corresponding to symmetry breaking phenomena. We show that these phase-transitions are always in a mean-field universality class, as they are the result of a self-consistency condition in the generative dynamics. We argue that the critical instability that arises from the phase transitions lies at the heart of their generative capabilities, which are characterized by a set of mean-field critical exponents. Finally, we show that the dynamic equation of the generative process can be interpreted as a stochastic adiabatic transformation that minimizes the free energy while keeping the system in thermal equilibrium.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次