Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation

通过福克-普朗克方程弥合基于得分的扩散模型中的常微分方程-随机微分方程差距

阅读:1

Abstract

Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling, due to both their mathematical foundations and their state-of-the art performance in many tasks. Empirically, it has been reported that samplers based on ordinary differential equations (ODEs) are inferior to those based on stochastic differential equations (SDEs). In this article, we systematically analyse the difference between the ODE and SDE dynamics of score-based diffusion models and show how this relates to an associated Fokker-Planck equation. We rigorously describe the full range of dynamics and approximations arising when training score-based diffusion models and derive a theoretical upper bound on the Wasserstein 2-distance between the ODE- and SDE-induced distributions in terms of a Fokker-Planck residual. We also show numerically that conventional score-based diffusion models can exhibit significant differences between ODE- and SDE-induced distributions that we demonstrate using explicit comparisons. Moreover, we show numerically that reducing this Fokker-Planck residual by adding it as an additional regularization term during training closes the gap between ODE- and SDE-induced distributions. Our experiments suggest that this regularization can improve the distribution generated by the ODE; however this can come at the cost of degraded SDE sample quality.This article is part of the theme issue 'Partial differential equations in data science'.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。