Add Initial SDVI Implementation #1758
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
|
Thanks, @treigerm! The PR looks in a great shape. Do you want me to take an extra look at some details? |
|
Thanks @fehiepsi! There wasn't anything in particular that I think needed attention. So if there's nothing which you think sticks out as problematic, I am happy for you to merge! |
fehiepsi
approved these changes
Mar 14, 2024
|
Yeah, your plan sounds good to me. |
OlaRonning
pushed a commit
to aleatory-science/numpyro
that referenced
this pull request
May 6, 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Outdated suggestions cannot be applied.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.
This is follow-up work from #1715 and now adding Support Decomposition VI (SDVI) which is a variational method for programs with stochastic support as discussed in #1697.
Once this is merged I will add a simple tutorial on how to use these algorithms properly. At the moment, only the most basic version of DCC and SDVI are implemented, so the idea is that over time we can gradually add more bells and whistles (most prominently run inference in different program paths in parallel). For now, I wanted to keep the implementation simple to keep the PRs at a reasonable size.