codepawlMar 31

Google's 200M-parameter time-series foundation model with 16k context

https://github.com/google-research/timesfm

GitHub - google-research/timesfm: TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. - google-research/timesfm

GitHub
Show threadEmilStenstromMar 31

I somehow find the concept of a general time series model strange. How can the same model predict egg prices in Italy, and global inflation in a reliable way?

And how would you even use this model, given that there are no explanations that help you trust where the prediction comes from…

Show threadbenob

I would say:

- decomposition: discover a more general form of Fourrier transform to untangle the underlying factors

- memorization: some patterns are recurrent in many domains such as power low

- multitask: exploit cross-domain connections such as weather vs electricity

Mar 31 at 6:03amWeb