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

A problem of "Domain notes" #1

Open
CRhapsody opened this issue Jan 10, 2023 · 0 comments
Open

A problem of "Domain notes" #1

CRhapsody opened this issue Jan 10, 2023 · 0 comments

Comments

@CRhapsody
Copy link

CRhapsody commented Jan 10, 2023

Hello,
In your README.md file of this project:

A variant of the original DeepPoly domain is implemented where the ReLU approximation is not heuristically choosing between two choices (either picking y = x or y = 0 as the new upper bound). Right now it is fixed to choosing y = 0, because there was Galois connection violation observed if this heuristic is enabled. Basically, it is observed in experiment that a smaller abstraction may unexpectedly incur larger safety distance than its containing larger abstraction.

I guess "either picking y = x or y = 0 as the new upper bound" may be "either picking y = x or y = 0 as the new lower bound".

And you said that there was Galois connection violation if the heuristic is enabled. Would you like to tell me if there is any paper or proof to support this appearance If it's not too much trouble?

Thank you!

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

1 participant