# Time Series Source Separation with Slow Flows

arXiv: https://arxiv.org/abs/2007.10182 · HTML: https://mlsanity.com/paper/2007.10182/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 1 of 1)

- [Universal hidden monotonic trend estimation with contrastive learning](https://mlsanity.com/paper/2210.09817/) (2022)

## Abstract (arXiv)

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.