search

thuml / Koopa

Code release for "Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors" (NeurIPS 2023), https://arxiv.org/abs/2305.18803
MIT License
186 stars 23 forks source link

Degree of Variation Experiment #15

Closed khan-yin closed 10 months ago

khan-yin commented 10 months ago

Hello Author，I am curious about two component features after Fourier Filter, can you tell me the details or show me the code how you did the visualization study on features and how can I calculate Degree of Variation

lichenyu20 commented 10 months ago

Hello, you can calculate Degree of Variation as follows:

  1. decompose the series into time-invariant component and time-variant component;
  2. utilize the two components to train MLPs;
  3. calculate the standard deviation of linear weighting.