Search Results for author:
Found 2 papers, 0 papers with code
Stability analysis of SGD through the normalized loss function
We prove new generalization bounds for stochastic gradient descent for both the convex and non-convex case.
On the implicit minimization of alternative loss functions when training deep networks
One approach to try to exploit such understanding would be to then make the bias explicit in the loss function.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
