arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.18804stat.MLcs.LGmath.STstat.TH
收藏

高维流形假设下扩散模型的收敛性

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

University of Oxford(牛津大学);CNRS(法国国家科学研究中心)

Iskander Azangulov, George Deligiannidis, Judith Rousseau

AI总结:

该研究在流形假设下证明 DDPM 的分数学习和采样复杂度均实现与高维 ambient 空间维度无关的速率,通过建立扩散模型与高斯过程极值理论的新框架完成,解释了其经验成功。

摘要:

去噪扩散概率模型(DDPM)是用于从高维数据分布生成合成数据的强大最先进方法,广泛应用于图像、音频、视频生成及科学领域的诸多应用中。流形假设指出,高维数据通常位于 ambient 空间中的低维流形上,且被广泛认为在给定示例中成立。尽管近期研究结果为扩散模型如何适配流形假设提供了宝贵见解,但尚未能解释这些模型的巨大经验成功,这使其成为极具成效的研究方向。本研究在流形假设下对 DDPM 展开研究,证明其在分数学习方面实现了与 ambient 维度无关的速率;在采样复杂度方面,关于 Wasserstein 距离也得到了与 ambient 维度无关的速率。研究通过开发将扩散模型与研究充分的高斯过程极值理论相连接的新框架完成上述工作。

英文摘要:

Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond. The \textit{manifold hypothesis} states that high-dimensional data often lie on lower-dimensional manifolds within the ambient space, and is widely believed to hold in provided examples. While recent results have provided invaluable insight into how diffusion models adapt to the manifold hypothesis, they do not capture the great empirical success of these models, making this a very fruitful research direction. In this work, we study DDPMs under the manifold hypothesis and prove that they achieve rates independent of the ambient dimension in terms of score learning. In terms of sampling complexity, we obtain rates independent of the ambient dimension w.r.t.\ the Wasserstein distance. We do this by developing a new framework connecting diffusion models to the well-studied theory of extrema of Gaussian Processes.

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。

↑