-
-
Notifications
You must be signed in to change notification settings - Fork 25.8k
FIX use correct formulation for ExpSineSquared kernel #20070
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
base: main
Are you sure you want to change the base?
Conversation
@glemaitre you still want this in v1.0? |
We need some cythonization here and it would be useful to come back once the PR of @jjerphan is merged. |
Seems that this needs a lot more work. Very unlikely to fit in 1.1 |
wont make it for 1.5. It's been in draft mode for several releases. I'm removing it from any milestone. Feel free to add it back when it's ready. |
@jjerphan the PRs you mentioned here are both closed. Could you maybe give us an update on the status of this part of the project? |
Yes! Both PRs have been superseded by #21462 which addressed a slightly different class of contributions than this one, namely reductions over pairwise distances matrices. In this regards, potential next efforts are non-exhaustively listed in #25888, and people should feel free to pick items or suggest other ones. There are other patterns of computations over dissimilarity matrices or kernel matrices which are similar but which aren't covered yet (we need to decide whether they could be relevant or not for scikit-learn, I think). I would refer you to other projects like Though I would like to help the project on this front, I unfortunately have other commitments for now. |
Wonderful! I am going through the EuroScipy 2022 slides linked and will choose one of the tasks in #25888 and create a pull request. |
closes #19343
closes #9824
TODO: