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.

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

changing the position of epsilon #16

Open
implus opened this issue Nov 15, 2019 · 2 comments
Open

changing the position of epsilon #16

implus opened this issue Nov 15, 2019 · 2 comments

Comments

@implus
Copy link

implus commented Nov 15, 2019

Hi, siyuan:

According to the discussion of this article https://zhuanlan.zhihu.com/p/91926094 and the post-discussion in this article between Feng Wang and the authors, it is suggested to implement the WS by changing the position of epsilon. As suggested by Feng Wang, epsilon should be inside the sqrt() function of std. Or you can choose a little bit complicated solution by introducing epsilon-shifted L2 regularizer as proposed in https://arxiv.org/pdf/1911.05920.pdf .

@joe-siyuan-qiao
Copy link
Owner

Thanks for the suggestions!

We've also encountered some NaNs in other experiments we later have. We will update this repo when doing the next major update.

I'm reading the Understanding the Disharmony paper. Very interesting and solid work!

Thanks.

@MohitLamba94
Copy link

Yes definitely, epsilon should be inside the sqrt() bracket. torch.sqrt is a major source of NaN

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants