Time series source separation with slow flows

ICML 2020

Time series source separation with slow flows

Jul 12, 2020
|
20 views
|
Details
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. Speakers: Edouard Pineau, Sebastien Razakarivony, Thomas Bonald

Comments
loading...