[proposed feature] Eve: Improving Stochastic Gradient Descent with Feedback #1329
Labels
feature
A request for a proper, new feature.
module: optimizer
Related to torch.optim
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Projects
Hi all,
I implemented a paper "Improving Stochastic Gradient Descent with Feedback" as called Eve.
Eve is a modified version of Adam, and outperforms other SGD algorithms on some benchmark tasks including image classification.
Please, give me any advice and code review.
The code is uploaded in this gist, and below:
The text was updated successfully, but these errors were encountered: