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 feel like this a case where documenting -inf will lead to more people trying out. If this is not mathematically meaningful, then we could be promoting a bad practice?
My $0.02 is that this should be restricted to (0, inf). I have only heard of people wanting to increase the learning rate when doing something like cosine annealing, a linear warmup and decay or a cyclic learning rate for much more complicated deep neural networks. In the context of a linear classifier, I think you want the whole method to be pretty well-behaved, and the algorithm will not converge if the learning rate increases.
So, I'm happy to change this and submit a pull request if other people are agreeable.
sklearn/linear_model/_stochastic_gradient.py
Ref #22115
Originally posted by @ogrisel in #22115 (comment)
@thomasjpfan
cc: @glemaitre
The text was updated successfully, but these errors were encountered: