MCMC uniform prior in linear space and NUTS - #507
Merged
markrosslonergan merged 7 commits intoAug 14, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Making PR now to avoid straying too far from project-SBN-dev and to allow for an easier time with upcoming bin/PROfit.cxx refactoring.
Some MCMC enhancements. Still WIP, but ready to merge as an first pass. Adds a new target class which will use a uniform prior in linear space even if the physics variables are in log space. (TODO: This doesn't actually check that the model is in log space first so that should be added.)
Adds No U-Turn Sampling and standard Hamiltonian Monte Carlo classes. Only NUTS is hooked up to a command line argument right now and only for the mcmc subcommand. More testing is needed to check that everything is working properly, but the few chains I made looked reasonable even if the trees for each step were growing much larger than one would expect.
The analytic gradient from Lee would be very interesting to test with NUTS/HMC.