FMPE with higher-dim conditions #1704
Open
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
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1704 +/- ##
=======================================
Coverage ? 84.65%
=======================================
Files ? 137
Lines ? 11489
Branches ? 0
=======================================
Hits ? 9726
Misses ? 1763
Partials ? 0
Flags with carried forward coverage won't be shown. Click here to find out more.
|
janfb
reviewed
Nov 17, 2025
| rtol: The relative tolerance for the ODE solver. | ||
| exact: Whether the exact log-determinant of the Jacobian or an unbiased | ||
| stochastic estimate thereof is calculated. | ||
| condition_shape: The shape of the condition tensor. |
Contributor
There was a problem hiding this comment.
this is without batch dim, so pure event shape, right? maybe specify this in the docstring.
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Outdated suggestions cannot be applied.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.
Fixes #1702
This PR addresses the bug for FMPE posterior sampling when the condition event dim is greater than 1. I also added a test which checks that the samples are the correct shape, similar to
posterior_nn_test.py::test_batched_score_sample_with_different_x, so there is some code repetition, but I think our minimal setup looks quite different when we are dealing with matrix variables so I think this is clearer than trying to fit it in the same test function.