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 2402.05933cs.LGcs.AI
收藏

频域中的时间序列扩散

Time Series Diffusion in the Frequency Domain

DAMTP(应用数学与理论物理系);University of Cambridge(剑桥大学)

Jonathan Crabbé, Nicolas Huynh, Jan Stanczuk, Mihaela van der Schaar

AI总结:

本文提出频域扩散模型,利用傅里叶分析作为归纳偏置,在频域中实现去噪分数匹配,实验表明其比时间域扩散模型更优,能更好捕捉时间序列分布。

摘要:

傅里叶分析一直是信号处理发展中的重要工具。这让我们思考,这一框架是否也能同样惠及生成建模。在本文中,我们通过时间序列扩散模型的视角来探讨这一问题。更具体地说,我们分析将时间序列表示在频域中是否为基于分数的扩散模型提供了一种有用的归纳偏置。通过从时间域中扩散的典型随机微分方程(SDE)公式出发,我们展示了在频域中会发生一个对偶扩散过程,并带有一个重要细微差别:布朗运动被我们称为镜像布朗运动所取代,其特征是其分量之间存在镜像对称性。基于这一见解,我们展示了如何调整去噪分数匹配方法,以在频域中实现扩散模型。这产生了频率扩散模型,我们将其与典型的时间扩散模型进行比较。我们在涵盖医疗保健和金融等多个领域的真实世界数据集上的实证评估表明,频率扩散模型比时间扩散模型更好地捕捉训练分布。我们通过展示这些数据集中的时间序列在频域中往往比在时间域中更局部化来解释这一观察结果,这使得它们在前者中更容易建模。我们所有的观察都指向傅里叶分析与扩散模型之间富有影响力的协同作用。

英文摘要:

Fourier analysis has been an instrumental tool in the development of signal processing. This leads us to wonder whether this framework could similarly benefit generative modelling. In this paper, we explore this question through the scope of time series diffusion models. More specifically, we analyze whether representing time series in the frequency domain is a useful inductive bias for score-based diffusion models. By starting from the canonical SDE formulation of diffusion in the time domain, we show that a dual diffusion process occurs in the frequency domain with an important nuance: Brownian motions are replaced by what we call mirrored Brownian motions, characterized by mirror symmetries among their components. Building on this insight, we show how to adapt the denoising score matching approach to implement diffusion models in the frequency domain. This results in frequency diffusion models, which we compare to canonical time diffusion models. Our empirical evaluation on real-world datasets, covering various domains like healthcare and finance, shows that frequency diffusion models better capture the training distribution than time diffusion models. We explain this observation by showing that time series from these datasets tend to be more localized in the frequency domain than in the time domain, which makes them easier to model in the former case. All our observations point towards impactful synergies between Fourier analysis and diffusion models.

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。

↑