Full functionality for Variance Reduction (as per Lykkegaard et al. 2023) - #71
Open
louisekluge wants to merge 48 commits into
Open
Full functionality for Variance Reduction (as per Lykkegaard et al. 2023)#71louisekluge wants to merge 48 commits into
louisekluge wants to merge 48 commits into
Conversation
…ngth of the fine chain
include suggestions Co-authored-by: Mikkel Bue <mikkelbue@gmail.com>
…to da_estimator
Co-authored-by: Mikkel Bue <mikkelbue@gmail.com>
…ngle-level sampling that throws an error for the MALA-Rosenbrock notebook.
…LA rosenbrock example
… sampling in ray.py
louisekluge
marked this pull request as draft
September 3, 2026 10:39
Include changes since fork.
promoted_coarse is seeded in DAChain.__init__ to stay length-aligned with the fine chain; the acceptance ratio reads promoted_coarse[-1] on the first iteration, so it cannot be empty. Expected length 1, matching chain_coarse and chain_fine.
Collaborator
Author
|
Sorry for the clutter, relevant changes are of course only in the chain.py, diagnostics.py, proposal.py, ray.py and sampler.py, as well as a minor correction to test_chain.py (the proposal chain gets an initial element). To my recollection, this is all correct and tested, the examples run through. |
louisekluge
marked this pull request as ready for review
September 3, 2026 14:42
Collaborator
Author
|
Watch out: there is a direct call to import ray in proposal.py, which can break the install if ray is not available. I'll investigate further. Edit: ray must exist in environment before tinyDA is installed, this issue has nothing to do with my PR. |
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.
This adds randomised subchain length and sample collecting for computing the unbiased multilevel estimator based on a MLDA chain.