Derived novel generalization bounds (see report here), implemented optimizer based on terms in bound (see new_optimizer.py
) and compared against L2 regularization on standard datasets (CIFAR10, MNIST, etc.)
-
Notifications
You must be signed in to change notification settings - Fork 0
kushaltirumala/generalization_bound_emp
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Novel generalization bounds for MLP's with ReLU activations
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published