Code for the paper: "Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss" (Chizat and Bach). The code is written in Julia. The experiment of the paper can be reproduced in the Jupyter notebook.
-
Notifications
You must be signed in to change notification settings - Fork 0
Code for the paper: "Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss" (Chizat and Bach)
License
lchizat/2020-implicit-bias-wide-2NN
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Code for the paper: "Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss" (Chizat and Bach)
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published