arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04411cs.LGcs.AI
收藏

基于基于得分的生成模型的几何结构

Geometry of Score Based Generative Models

Northeastern University(东北大学)

Sandesh Ghimire, Jinyang Liu, Armand Comas, Davin Hill, Aria Masoomi, Octavia Camps, Jennifer Dy

摘要:

在这项工作中,我们从几何角度来看待基于得分的生成模型(也称为扩散生成模型)。从一个新的角度证明了在概率测度空间中,加噪声和由噪声生成的前向过程和后向过程都是Wasserstein梯度流。我们是第一个证明这种联系的人。我们对基于分数(和扩散)的生成模型的理解已经成熟,并通过借鉴贝叶斯推理,控制理论,随机微分方程和薛定谔桥等不同领域的思想变得更加完整。然而,许多悬而未决的问题和挑战依然存在。例如,一个问题是如何减少采样时间?我们证明,从几何的角度来看,使我们能够回答许多这些问题,并提供新的解释,一些已知的结果。此外,几何角度使我们能够设计一个直观的几何解决方案的问题,更快的采样。通过对传统的基于得分的生成模型增加投影步骤,我们证明了我们可以用更少的采样步骤生成高质量的图像。

英文摘要:

In this work, we look at Score-based generative models (also called diffusion generative models) from a geometric perspective. From a new view point, we prove that both the forward and backward process of adding noise and generating from noise are Wasserstein gradient flow in the space of probability measures. We are the first to prove this connection. Our understanding of Score-based (and Diffusion) generative models have matured and become more complete by drawing ideas from different fields like Bayesian inference, control theory, stochastic differential equation and Schrodinger bridge. However, many open questions and challenges remain. One problem, for example, is how to decrease the sampling time? We demonstrate that looking from geometric perspective enables us to answer many of these questions and provide new interpretations to some known results. Furthermore, geometric perspective enables us to devise an intuitive geometric solution to the problem of faster sampling. By augmenting traditional score-based generative models with a projection step, we show that we can generate high quality images with significantly fewer sampling-steps.

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。

↑