Repository navigation
Covmat disperse - #492
Open
cmbant wants to merge 9 commits into
Open
Covmat disperse#492cmbant wants to merge 9 commits into
cmbant wants to merge 9 commits into
Conversation
# Conflicts: # cobaya/component.py # cobaya/cosmo_input/convert_cosmomc.py # cobaya/grid_tools/batchjob.py # cobaya/input.py # cobaya/likelihoods/base_classes/bao.py # cobaya/prior.py # cobaya/tools.py
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 pull request introduces the ability to disperse initial chain starting points using the proposal covariance matrix (covmat) for correlated multivariate normal draws, rather than independent per-parameter dispersion. This is particularly useful for initializing MCMC chains in a way that respects parameter correlations, which can improve sampling efficiency (e.g. see #265). The implementation includes changes to
cobaya/prior.py,cobaya/model.py, and the MCMC sampler itself, as well as documentation and configuration updates. Additionally, several minor improvements and code style cleanups are included.New Feature: Disperse Initial Points Using Proposal Covmat
disperse_initial_with_covmat) to the MCMC sampler to disperse initial points using the proposal covmat, controlled via the YAML config. If enabled and a covmat is provided, initial points are drawn from a correlated multivariate normal distribution. [1] [2] [3]Prior.reference()andModel.get_valid_point()for anoverride_covmatparameter, which triggers correlated initial draws using the provided covariance matrix. [1] [2] [3] [4] [5]_reference_with_covmatinPriorto handle the logic for generating a reference point with a given covariance matrix, including documentation and robust handling of edge cases.AI generated, tested by @raphkou (#491, thanks!)