A Note on the Convergence of Denoising Diffusion Probabilistic Models
SD Mbacke, O Rivasplata - arXiv preprint arXiv:2312.05989, 2023 - arxiv.org
arXiv preprint arXiv:2312.05989, 2023•arxiv.org
Diffusion models are one of the most important families of deep generative models. In this
note, we derive a quantitative upper bound on the Wasserstein distance between the data-
generating distribution and the distribution learned by a diffusion model. Unlike previous
works in this field, our result does not make assumptions on the learned score function.
Moreover, our bound holds for arbitrary data-generating distributions on bounded instance
spaces, even those without a density wrt the Lebesgue measure, and the upper bound does …
note, we derive a quantitative upper bound on the Wasserstein distance between the data-
generating distribution and the distribution learned by a diffusion model. Unlike previous
works in this field, our result does not make assumptions on the learned score function.
Moreover, our bound holds for arbitrary data-generating distributions on bounded instance
spaces, even those without a density wrt the Lebesgue measure, and the upper bound does …
Diffusion models are one of the most important families of deep generative models. In this note, we derive a quantitative upper bound on the Wasserstein distance between the data-generating distribution and the distribution learned by a diffusion model. Unlike previous works in this field, our result does not make assumptions on the learned score function. Moreover, our bound holds for arbitrary data-generating distributions on bounded instance spaces, even those without a density w.r.t. the Lebesgue measure, and the upper bound does not suffer from exponential dependencies. Our main result builds upon the recent work of Mbacke et al. (2023) and our proofs are elementary.
arxiv.org
以上显示的是最相近的搜索结果。 查看全部搜索结果