New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

the implementation of SGDW is not consistent with paper? #433

Open

twmht opened this issue Apr 20, 2022 · 0 comments

twmht commented Apr 20, 2022 •

edited

Loading

I found out paper said that

they subtract p * weight_decay * learning_rate from p.

but from your implementation (https://github.com/jettify/pytorch-optimizer/blob/master/torch_optimizer/sgdw.py#L121),

you only subtract weight_decay * learning_rate from p.

Any idea?

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment