OrthogonalAdditiveGP with component-wise inference#3187
Closed
SebastianAment wants to merge 1 commit into
Closed
Conversation
meta-cla
Bot
added
the
CLA Signed
|
@SebastianAment has exported this pull request. If you are a Meta employee, you can view the originating Diff in D92461397. |
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Feb 17, 2026
Summary: This commit adds a new additive Gaussian process model `OrthogonalAdditiveGP`, which leverages the `OrthogonalAdditiveKernel`, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum. This is enabled with the refactored GPyTorch posterior inference stack via `_get_test_prior_mean_and_covariances`. This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the *sum* of the additive components. Reviewed By: hvarfner Differential Revision: D92461397
SebastianAment
force-pushed
the
export-D92461397
branch
from
f280347 to
50bd553
Compare
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Feb 17, 2026
Summary: This commit adds a new additive Gaussian process model `OrthogonalAdditiveGP`, which leverages the `OrthogonalAdditiveKernel`, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum. This is enabled with the refactored GPyTorch posterior inference stack via `_get_test_prior_mean_and_covariances`. This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the *sum* of the additive components. Reviewed By: hvarfner Differential Revision: D92461397
SebastianAment
force-pushed
the
export-D92461397
branch
from
50bd553 to
9cc1864
Compare
SebastianAment
force-pushed
the
export-D92461397
branch
from
9cc1864 to
fa61f33
Compare
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Mar 5, 2026
Summary: This commit adds a new additive Gaussian process model `OrthogonalAdditiveGP`, which leverages the `OrthogonalAdditiveKernel`, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum. This is enabled with the refactored GPyTorch posterior inference stack via `_get_test_prior_mean_and_covariances`. This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the *sum* of the additive components. Reviewed By: hvarfner Differential Revision: D92461397
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #3187 +/- ##
========================================
Coverage 99.98% 99.98%
========================================
Files 219 220 +1
Lines 21567 21732 +165
========================================
+ Hits 21564 21729 +165
Misses 3 3 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Mar 6, 2026
Summary: This commit adds a new additive Gaussian process model `OrthogonalAdditiveGP`, which leverages the `OrthogonalAdditiveKernel`, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum. This is enabled with the refactored GPyTorch posterior inference stack via `_get_test_prior_mean_and_covariances`. This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the *sum* of the additive components. Reviewed By: hvarfner Differential Revision: D92461397
SebastianAment
force-pushed
the
export-D92461397
branch
from
fa61f33 to
1275352
Compare
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Mar 6, 2026
Summary: This commit adds a new additive Gaussian process model `OrthogonalAdditiveGP`, which leverages the `OrthogonalAdditiveKernel`, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum. This is enabled with the refactored GPyTorch posterior inference stack via `_get_test_prior_mean_and_covariances`. This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the *sum* of the additive components. Reviewed By: hvarfner Differential Revision: D92461397
SebastianAment
force-pushed
the
export-D92461397
branch
from
1275352 to
bcb2788
Compare
Summary: This commit adds a new additive Gaussian process model `OrthogonalAdditiveGP`, which leverages the `OrthogonalAdditiveKernel`, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum. This is enabled with the refactored GPyTorch posterior inference stack via `_get_test_prior_mean_and_covariances`. This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the *sum* of the additive components. Reviewed By: hvarfner Differential Revision: D92461397
SebastianAment
force-pushed
the
export-D92461397
branch
from
bcb2788 to
e397819
Compare
|
This pull request has been merged in 6866ad6. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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:
This commit adds a new additive Gaussian process model
OrthogonalAdditiveGP, which leverages theOrthogonalAdditiveKernel, and importantly, posterior inference of individual additive components, conditioned on noisy observations of the sum.This is enabled with the refactored GPyTorch posterior inference stack via
_get_test_prior_mean_and_covariances.This relies on having an additional batch dimension for the test-test and train-test covariance, corresponding to the kernel matrices of each additive component, while the batch dimension has to be absent on the training set, because we are observing the sum of the additive components.
Reviewed By: hvarfner
Differential Revision: D92461397