-
-
Notifications
You must be signed in to change notification settings - Fork 25.9k
WIP ENH Added auto
option to FastICA.whiten_solver
#23616
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
…into whiten_auto
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. Thanks @Micky774
@glemaitre I changed the warning a bit to be more explicit about future backwards incompatibility, per a conversation @thomasjpfan and I had. Just wanted to let you know in case it affects your review :) |
May you include a link to the benchmarks you did in the opening comment in this PR? This way it is easier to find when someone is trying to see why it is set to |
Very good point, done! |
auto
option to FastICA.whiten_solver
auto
option to FastICA.whiten_solver
Changing to WIP until a better heuristic is found (or at least a better justification) |
Reference Issues/PRs
Follow-up to #22527
What does this implement/fix? Explain your changes.
Added
auto
option toFastICA.whiten_solver
along w/ tests, beginning deprecation to adoptauto
as default value forwhiten_solver
.Any other comments?
For justification of
>50x
heuristic in choosing solver, please see this gist which contains the generating benchmark script as well as a copy of my results.