Re:Are deep neural networks dramatically overfitted? (2019)
by GregarianChild on Monday April 05, 2021 @08:40AM
(#26698198)
In practise, how do you know if SDG has converged to a global optimum, and do you let it run long enough in practise until covergence?
Re:Are deep neural networks dramatically overfitted? (2019)
by unishark on Monday April 05, 2021 @09:50AM
(#26698929)
You don't know. The point was even if you did get there it could still be an overfit model you don't want, since it's based on a training data set, not the true statistics of the distribution the samples come from.
Though personally I do find a lot this modern "experimental" research quite hokey. I don't think this is something academics should be getting research funding to pursue. This is engineers building intuition about how to tune their product.