add option for using posterior predictive in cross-validation #2517
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D58227612 |
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2517 +/- ##
=======================================
Coverage 95.21% 95.21%
=======================================
Files 485 485
Lines 47238 47256 +18
=======================================
+ Hits 44978 44996 +18
Misses 2260 2260 ☔ View full report in Codecov by Sentry. |
|
This pull request was exported from Phabricator. Differential Revision: D58227612 |
sdaulton
added a commit
to sdaulton/Ax-1
that referenced
this pull request
Jun 13, 2024
…ok#2517) Summary: Pull Request resolved: facebook#2517 see title. This change is particularly important for model selection using the NLL if we have noisy observations. Using the posterior over the true function and not the noisy observations gives quite misleading results about model calibration. I also think that predicted vs actual plots from LOOCV are insightful when using the posterior predictive when the observations are noisy. We may want to consider adding observation_noise to `predict`, but we can do that in a follow-up. Differential Revision: D58227612
sdaulton
force-pushed
the
export-D58227612
branch
from
45cc46c
to
0d7a1ed
Compare
|
This pull request was exported from Phabricator. Differential Revision: D58227612 |
sdaulton
added a commit
to sdaulton/Ax-1
that referenced
this pull request
Jun 13, 2024
…ok#2517) Summary: Pull Request resolved: facebook#2517 see title. This change is particularly important for model selection using the NLL if we have noisy observations. Using the posterior over the true function and not the noisy observations gives quite misleading results about model calibration. I also think that predicted vs actual plots from LOOCV are insightful when using the posterior predictive when the observations are noisy. We may want to consider adding observation_noise to `predict`, but we can do that in a follow-up. Reviewed By: Balandat Differential Revision: D58227612
sdaulton
force-pushed
the
export-D58227612
branch
from
0d7a1ed
to
c42728d
Compare
…ok#2517) Summary: Pull Request resolved: facebook#2517 see title. This change is particularly important for model selection using the NLL if we have noisy observations. Using the posterior over the true function and not the noisy observations gives quite misleading results about model calibration. I also think that predicted vs actual plots from LOOCV are insightful when using the posterior predictive when the observations are noisy. We may want to consider adding observation_noise to `predict`, but we can do that in a follow-up. Reviewed By: Balandat Differential Revision: D58227612
|
This pull request was exported from Phabricator. Differential Revision: D58227612 |
sdaulton
force-pushed
the
export-D58227612
branch
from
c42728d
to
9f8e4bc
Compare
|
This pull request has been merged in 4ef840b. |
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.
Summary:
see title. This change is particularly important for model selection using the NLL if we have noisy observations. Using the posterior over the true function and not the noisy observations gives quite misleading results about model calibration.
I also think that predicted vs actual plots from LOOCV are insightful when using the posterior predictive when the observations are noisy. We may want to consider adding observation_noise to
predict, but we can do that in a follow-up.Differential Revision: D58227612