arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.06281cs.LGcs.CV
收藏

揭秘变分扩散模型

Demystifying Variational Diffusion Models

Imperial College London(伦敦帝国理工学院)

Fabio De Sousa Ribeiro, Ben Glocker

AI总结:

本文通过有向图建模和变分推断原理,为扩散模型提供统一易懂的视角,降低入门门槛,帮助理解其与分层潜变量模型的关系。

摘要:

尽管扩散模型引起了越来越多的关注,但深入理解这类模型仍然是一项难以捉摸的工作,尤其是对于不熟悉非平衡统计物理的初学者而言。得益于该领域快速的发展速度,现有关于扩散模型的大多数工作要么聚焦于应用,要么聚焦于理论贡献。不幸的是,理论材料往往对从业者和新研究人员来说难以理解,导致正在进行的研究中存在表面化理解的风险。鉴于扩散模型如今已成为不可或缺的工具,需要一种清晰且统一的视角来看待这类模型,以便恰当地将生成建模的最新进展置于背景中,并降低新研究人员的入门门槛。为此,我们重新审视了扩散模型的先驱,如分层潜变量模型,并仅使用有向图建模和变分推断原理综合出一个整体视角。由此产生的叙述更容易理解,因为它相对于非平衡热力学或随机微分方程的视角,对普通读者施加了更少的先决条件。

英文摘要:

Despite the growing interest in diffusion models, gaining a deep understanding of the model class remains an elusive endeavour, particularly for the uninitiated in non-equilibrium statistical physics. Thanks to the rapid rate of progress in the field, most existing work on diffusion models focuses on either applications or theoretical contributions. Unfortunately, the theoretical material is often inaccessible to practitioners and new researchers, leading to a risk of superficial understanding in ongoing research. Given that diffusion models are now an indispensable tool, a clear and consolidating perspective on the model class is needed to properly contextualize recent advances in generative modelling and lower the barrier to entry for new researchers. To that end, we revisit predecessors to diffusion models like hierarchical latent variable models and synthesize a holistic perspective using only directed graphical modelling and variational inference principles. The resulting narrative is easier to follow as it imposes fewer prerequisites on the average reader relative to the view from non-equilibrium thermodynamics or stochastic differential equations.

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。

↑