Update feature scaling #2165
Merged
Update feature scaling #2165
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
RoyStegeman
force-pushed
the
update_fs
branch
from
04c45aa to
f934deb
Compare
scarlehoff
reviewed
Oct 16, 2024
| "chi2": 1.4108729362487793, | ||
| "erf_tr": 2.803447723388672, | ||
| "erf_vl": 2.2027039527893066, | ||
| "chi2": 1.5391007661819458, |
There was a problem hiding this comment.
Yes slightly, I think it's because now the x=1 is usually included in the scaled xgrid where before it was not
There was a problem hiding this comment.
and why is it needed? Its contribution should be 0.
There was a problem hiding this comment.
Because previously x=1 was not in the fktable xgrids so I could just use the largest x-grid point as the last step in the grid before x=1. With pineappl x=1 is there and it should remain at 1.
Before this change the x=1 in pineappl would be the last step/interval before 1 after scaling.
scarlehoff
approved these changes
Oct 16, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Some modifications to the feature scaling, in particular it makes sure that the input passed tot he photon computation is the correct one. This is because with feature scaling we pass both the scale and non-scaled input to the model, where the non-scaled input is used in the computation of sum rules and integrability.
Some reports of fits with this branch are: