arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.03368cs.LGstat.ML
收藏

生成扩散模型中的潜在抽象

Latent Abstractions in Generative Diffusion Models

EURECOM(欧洲电信研究院);CNRS(法国国家科学研究中心);SAP Labs(思爱普实验室)

Giulio Franzese, Mattia Martini, Giulio Corallo, Paolo Papotti, Pietro Michiardi

AI总结:

本文提出扩展NLF的理论框架,将扩散模型刻画为由潜在抽象引导的非线性滤波SDE系统,并通过实证研究验证潜在抽象在生成过程中的涌现。

摘要:

在这项工作中,我们研究基于扩散的生成模型如何通过隐式依赖一组低维潜在抽象的显现来生成高维数据(如图像),这些潜在抽象引导着生成过程。我们提出了一个新的理论框架,该框架扩展了NLF,并为基于SDE的生成模型提供了独特的视角。我们的理论发展依赖于对联合(状态与测量)动力学的全新表述,以及一种衡量系统状态对测量过程影响的信息论度量。根据我们的理论,扩散模型可以被表述为一个SDE系统,描述一个非线性滤波器,其中不可观测的潜在抽象的演化引导着可观测测量过程(对应于生成路径)的动力学。此外,我们进行了一项实证研究,以验证我们的理论以及先前关于潜在抽象在生成过程不同阶段涌现的实证结果。

英文摘要:

In this work we study how diffusion-based generative models produce high-dimensional data, such as an image, by implicitly relying on a manifestation of a low-dimensional set of latent abstractions, that guide the generative process. We present a novel theoretical framework that extends NLF, and that offers a unique perspective on SDE-based generative models. The development of our theory relies on a novel formulation of the joint (state and measurement) dynamics, and an information-theoretic measure of the influence of the system state on the measurement process. According to our theory, diffusion models can be cast as a system of SDE, describing a non-linear filter in which the evolution of unobservable latent abstractions steers the dynamics of an observable measurement process (corresponding to the generative pathways). In addition, we present an empirical study to validate our theory and previous empirical results on the emergence of latent abstractions at different stages of the generative process.

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。

↑