Skip to content

Eval sign flipping #22

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

Closed
devnkong opened this issue Jun 6, 2022 · 3 comments
Closed

Eval sign flipping #22

devnkong opened this issue Jun 6, 2022 · 3 comments

Comments

@devnkong
Copy link

devnkong commented Jun 6, 2022

Hi Vijay,

Thanks for your repo!

Question: I see your doing sign flipping of eigen pos_enc during training, but it seems that you are not doing so during eval time. I understand that we want to make deterministic predictions so we don't have random flipping when evaluating it. Do you have further comments or justification for this?

Best
Kezhi

@devnkong
Copy link
Author

devnkong commented Jun 8, 2022

Also do you have some reason for choosing eigen vectors with small eigen values?

@vijaydwivedi75
Copy link
Member

Hi @devnkong, thanks for your questions.

Q: Why sign flipping is not used during eval?
A: The random sign flipping during the training is to allow the network to be invariant or independent of the choices among 2^k possibilities. By this approach then, the sign flipping is not required during eval.

Q: choosing eigen vectors with small eigen values?
A: Please refer to Section E.1.2 in https://arxiv.org/pdf/2003.00982.pdf

Best,
Vijay

@devnkong
Copy link
Author

Thanks!

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

2 participants