Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
From MaRDI portal
Publication:6420346
arXiv2212.06359MaRDI QIDQ6420346
Author name not available (Why is that?)
Publication date: 12 December 2022
Abstract: Score-based generative models are shown to achieve remarkable empirical performances in various applications such as image generation and audio synthesis. However, a theoretical understanding of score-based diffusion models is still incomplete. Recently, Song et al. showed that the training objective of score-based generative models is equivalent to minimizing the Kullback-Leibler divergence of the generated distribution from the data distribution. In this work, we show that score-based models also minimize the Wasserstein distance between them under suitable assumptions on the model. Specifically, we prove that the Wasserstein distance is upper bounded by the square root of the objective function up to multiplicative constants and a fixed constant offset. Our proof is based on a novel application of the theory of optimal transport, which can be of independent interest to the society. Our numerical experiments support our findings. By analyzing our upper bounds, we provide a few techniques to obtain tighter upper bounds.
Has companion code repository: https://github.com/uw-madison-lee-lab/score-wasserstein
This page was built for publication: Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6420346)
