Sample-Efficient Training for Score-Based Diffusion

Shivam Gupta, Aditya Parulekar, Eric Price, Zhiyang XunOpenReview 2024 · Submission to ICLR 2024 · Rejected · OpenReview

Abstract

Score-based diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. Recently, a number of theoretical works \citep{chen2022, Chen2022ImprovedAO, chen2023probability, benton2023linear} have shown that diffusion models can efficiently sample, assuming $L^2$-accurate score estimates. The score-matching objective naturally approximates the true score in $L^2$, but the sample complexity of existing bounds depends \emph{polynomially} on the data radius and desired Wasserstein accuracy. By contrast, the time complexity of sampling is only logarithmic in these parameters. We show that estimating the score in $L^2$ \emph{requires} this polynomial dependence, but that polylogarithmic samples actually do suffice for sampling. We show that with a polylogarithmic number of samples, the ERM of the score-matching objective is $L^2$ accurate on all but a probability $\delta$ fraction of the true distribution, and that this weaker guarantee is sufficient for efficient sampling.
BibTeX
@misc{gupta2024sample,
  author = {Shivam Gupta and Aditya Parulekar and Eric Price and Zhiyang Xun},
  title = {{Sample-Efficient Training for Score-Based Diffusion}},
  year = {2024},
  url = {https://openreview.net/forum?id=qOgLmcJxxF},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2024},
}
Figure