[go: up one dir, main page]

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

Update faq.md #203

Merged
merged 6 commits into from
May 2, 2022
Merged

Update faq.md #203

merged 6 commits into from
May 2, 2022

Conversation

Dref360
Copy link
Member
@Dref360 Dref360 commented Apr 20, 2022

Summary:

First pass at trying to answer some common questions.
Let me know if this is useful and which questions should we add?

Features:

Checklist:

  • Your code is documented (To validate this, add your module to tests/documentation_test.py).
  • Your code is tested with unit tests.
  • You moved your Issue to the PR state.

@Dref360 Dref360 requested a review from parmidaatg April 20, 2022 15:15
Copy link
Collaborator
@parmidaatg parmidaatg left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

amazing :)

docs/faq.md Outdated Show resolved Hide resolved
docs/faq.md Outdated Show resolved Hide resolved
### Which query size to use?

Of course the lower the better, but [Atighehchian et al.](https://arxiv.org/abs/2006.09916) shows that BALD works well with a query size under 1000. This was tested on an academic dataset where Random sampling is especially strong. In practice, BALD performs worse on low-diversity datasets and could wrongly behave on a lower query size.


Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lets add a section on what to do if the test and train distribution are different (actually this can be a tutorial) wdyt?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm not sure I understand? What happens when the train and test distributions are different?

docs/faq.md Show resolved Hide resolved
Dref360 and others added 2 commits April 26, 2022 12:15
Co-authored-by: Parmida Atighehchian <parmidaatg@users.noreply.github.com>
docs/faq.md Outdated Show resolved Hide resolved
docs/faq.md Outdated Show resolved Hide resolved
@Dref360 Dref360 requested a review from parmidaatg April 26, 2022 21:20
Dref360 and others added 2 commits April 27, 2022 08:59
Co-authored-by: Parmida Atighehchian <parmidaatg@users.noreply.github.com>
@parmidaatg parmidaatg merged commit 8c975ea into master May 2, 2022
@parmidaatg parmidaatg deleted the faq-theory branch May 2, 2022 15:29
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

Successfully merging this pull request may close these issues.

2 participants