News for hackers. Stuff that matters.
Re:Every Model Learned by Gradient Descent Is Approximately ... by blackbear_ on Monday December 07, 2020 @04:18AM (#25330574)
Interesting to compare this with [1], which shows that for some concept classes neural networks trained with SGD are much easier to train (i.e., require less data).

In other words, even though these two types of model are in a way equivalent, one can be much easier to train than the other for certain concepts (no free lunch).

[1] https://arxiv.org/abs/2001.04413

There are no comments on this comment yet.