You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I wrote a better init in TensorLy-Torch) we should probably bring it in at some point, it allows the reconstruction to have zero mean and given standard deviation.
The text was updated successfully, but these errors were encountered:
I had a look at your code @JeanKossaifi, if I got it correctly its simply a matter of scaling the standard deviation with the rank and the order; seems like we could indeed very easily have this is pure tensorly code without any issue.
I'd be happy to review the PR quickly if you want to open the PR. Only thing I would add is a quick math explanation of the computation in the comments.
I wrote a better init in TensorLy-Torch) we should probably bring it in at some point, it allows the reconstruction to have zero mean and given standard deviation.
The text was updated successfully, but these errors were encountered: