Allow draws from Weibull, MvStudentT, LKJCorr and LKJCholeskyCovRV in alternative backends
#7685
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
ricardoV94
force-pushed
the
more_symboic_rvs
branch
5 times, most recently
from
431666f to
5e57d03
Compare
ricardoV94
force-pushed
the
more_symboic_rvs
branch
from
5e57d03 to
b5de436
Compare
ricardoV94
changed the title
Weibull, MvStudentT, LKJCorr and LKJCholeskyCovRV can now be sampled in alternative backends
ricardoV94
changed the title
Weibull, MvStudentT, LKJCorr and LKJCholeskyCovRV can now be sampled in alternative backends Weibull, MvStudentT, LKJCorr and LKJCholeskyCovRV in alternative backends
ricardoV94
force-pushed
the
more_symboic_rvs
branch
from
b5de436 to
02a5a36
Compare
|
I added an option to forward the decomposition method to the underlying MvNormal. This will require the next PyTensor release |
ricardoV94
force-pushed
the
more_symboic_rvs
branch
4 times, most recently
from
374e582 to
b7f4fc5
Compare
ricardoV94
force-pushed
the
more_symboic_rvs
branch
from
b7f4fc5 to
999d4a2
Compare
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #7685 +/- ##
==========================================
+ Coverage 83.15% 92.83% +9.67%
==========================================
Files 107 107
Lines 18313 18320 +7
==========================================
+ Hits 15228 17007 +1779
+ Misses 3085 1313 -1772
🚀 New features to boost your workflow:
|
ricardoV94
force-pushed
the
more_symboic_rvs
branch
from
7dd770b to
48ffc97
Compare
jessegrabowski
approved these changes
Mar 7, 2025
| z = z / pt.sqrt(pt.einsum("ij,ij->i", z, z.copy()))[..., np.newaxis] | ||
| P = P[..., 0:mp1, mp1].set(pt.sqrt(y[..., np.newaxis]) * z) | ||
| P = P[..., mp1, mp1].set(pt.sqrt(1.0 - y)) | ||
| C = pt.einsum("...ji,...jk->...ik", P, P.copy()) |
There was a problem hiding this comment.
Would P.mT @ P just work here? We know P will always be at least 2d.
There was a problem hiding this comment.
Einsum should arrive at the same thing though
There was a problem hiding this comment.
Sure, and I love einsum more than the average person, and actually find it more readable. Just curious what you thought about the alternative
There was a problem hiding this comment.
The .mt @ is a bit more direct (avoids the OFG that is inlined later), this makes it easier to review the changes :)
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.
This PR converts more RandomVariable Ops to SymbolicRandomVariable (built on top of other RV Ops), which makes them automatically compatible with alternative backends.
Depends on:
pymc-devs/pytensor#1222
pymc-devs/pytensor#1223
📚 Documentation preview 📚: https://pymc--7685.org.readthedocs.build/en/7685/