Add spatial derivatives to squar_sin_exp kernel #582
Merged
Conversation
This file contains hidden or 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
new definition of a problem for squar_sin_exp, as the previous one was modeled by a constant line in one direction, creating a division by zero in the computation of the relative error. Also, a new computation for the error on the derivative of the variance is introduced, in order to account for when value can be so close to zero that the relative difference doesn't make much sense anymore.
relf
requested changes
Jun 27, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Note that in order to make this derivative work a dummy variable is used, "dd", and passed to the kernel while being 0 and not be used. This is because squar_sin_exp has 2 times more hyperparameter than the other kernels, so some code has to be bypassed.
Some tests with finite differences have been relaxed, in order to account for the possibility of having a finite difference of 0 and a real derivative that is a very small number (giving a relative error of infinity), see the formula of np.testing.assert_allclose for more details.