In this paper, we show that slow feature analysis (SFA), a common time series decomposition method, naturally fits into the flow-based models (FBM) framework, a type of invertible neural latent variable models. Building upon recent advances on blind source separation, we show that such a fit makes the time series decomposition identifiable.

翻译：在本文中,我们表明慢速特征分析(SFA)是一种共同的时间序列分解方法,它自然地适合流动模型框架(FBM),一种不可忽略的神经潜伏变量模型。 在盲人源分离的最新进展的基础上,我们证明这种功能使得时间序列分解可以识别。