A few months ago I asked how time series shorter than input

Question

A few months ago I asked how time series shorter than input size were handled whether they were padded or ignored and was told that zero padding was used < Cristian Nixtla > Could you explain what changed with this commit Thank you very much

Cristian (Nixtla) · Answer

Hi < Manuel> Yes Previously we padded time series with zeros to make them of same size internally in the temporal tensor However this only applied to complete shorter time series compared to longer series We realized that when all time series were shorter than input size it was raising errors Now we are adding this extra padding for the case when all time series are shorter than input size Sorry for the confusion

Cristian (Nixtla) · Answer

Even with this fix it is not recommended to train models in this extreme case where all time series are too short The model will only have 1 window to train per series Statistical models will probably work better

Manuel · Answer

< Cristian Nixtla > Thank you Does the new additional padding have available mask=0

Cristian (Nixtla) · Answer

Yes