无限维扩散模型
Infinite-Dimensional Diffusion Models
AI总结:
本文提出直接在无限维空间构建扩散生成模型,证明其适定性并给出与维度无关的样本到目标测度距离界,为函数生成及多类分布建模提供设计指导。
摘要:
扩散模型已对许多应用领域产生深远影响,其中包括图像或时间序列等数据本质上具有无限维特征的领域。标准方法是先进行离散化,然后将扩散模型应用于离散化后的数据。尽管这类方法在实践中具有吸引力,但随着离散化参数被细化,所得算法的性能通常会下降。本文转而直接在无限维中表述基于扩散的生成模型,并将其应用于函数的生成建模。我们证明了这些表述在无限维情形下是适定的,并给出了从样本到目标测度的与维度无关的距离界。利用该理论,我们还提出了设计无限维扩散模型的指导原则。对于图像分布,这些指导原则与当前的典型选择一致;但对于其他分布,我们能够改进这些典型选择。我们通过将算法应用于流形上的数据分布,以及贝叶斯逆问题或基于模拟的推断中出现的分布,从理论和实验两方面展示了这些结果。
英文摘要:
Diffusion models have had a profound impact on many application areas, including those where data are intrinsically infinite-dimensional, such as images or time series. The standard approach is first to discretize and then to apply diffusion models to the discretized data. While such approaches are practically appealing, the performance of the resulting algorithms typically deteriorates as discretization parameters are refined. In this paper, we instead directly formulate diffusion-based generative models in infinite dimensions and apply them to the generative modelling of functions. We prove that our formulations are well posed in the infinite-dimensional setting and provide dimension-independent distance bounds from the sample to the target measure. Using our theory, we also develop guidelines for the design of infinite-dimensional diffusion models. For image distributions, these guidelines are in line with current canonical choices. For other distributions, however, we can improve upon these canonical choices. We demonstrate these results both theoretically and empirically, by applying the algorithms to data distributions on manifolds and to distributions arising in Bayesian inverse problems or simulation-based inference.
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。