Skip to content
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

rezero with norm #4

Closed
AllenDun opened this issue Mar 13, 2020 · 1 comment
Closed

rezero with norm #4

AllenDun opened this issue Mar 13, 2020 · 1 comment

Comments

@AllenDun
Copy link

great work! In your paper, rezero shows two main benefits both in deeper learning and faster convergence. Various forms of norm and residual connections are listd In Table 1. I am curious about the form of rezero with norm, e.g., x(i+1) = x(i) + aF(Norm(x(i))). Will it be worse or better?
Thanks
@majumderb
Copy link
Owner

Hi, thanks for your comment. Your equation corresponds to prenorm, Table 1, row 4. We show that Pre-norm performs as worse as GPT-norm compared to ReZero in the case of Transformers.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@AllenDun @majumderb