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

Why not directly use Emb(W) as X_0? #56

Open
leekum2018 opened this issue Jan 12, 2023 · 2 comments
Open

Why not directly use Emb(W) as X_0? #56

leekum2018 opened this issue Jan 12, 2023 · 2 comments

Comments

@leekum2018
Copy link

leekum2018 commented Jan 12, 2023 •
edited
Loading

Thanks for your nice work. I have a question and have difficulty understanding it, that is, why not directly use $Emb(W)$ as $X_0$, instead, $X_0 = Emb(W)+ N(0, \sigma_0 I)$ in the paper. Looking forward to your reply, thanks!
@Dawn-LX
Copy link

Dawn-LX commented Feb 20, 2023

+1, I also have this question

@mimbres
Copy link

mimbres commented Mar 16, 2023 •
edited
Loading

FYI, this was discussed in openreivew. $\sigma_0$ is set to 0.0001 and it becomes spiky Gaussian, and it was empirical choice according to the authors.

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
3 participants
@mimbres @leekum2018 @Dawn-LX