Skip to content

Conversation

alecksphillips
Copy link
Collaborator

@alecksphillips alecksphillips commented Sep 27, 2023

Fix #52 .

I've also simplified the gathering of outputs on MPI by doing a "gather" before returning the samples (in the form of SMCOutput). This also has the benefit of abstracting the MPI-gathering of samples away from the user.

This can be disabled by setting gather_all=False when calling the sampler:

DiscreteVariableSMC.sample(Tsmc, N, gather_all = False)

Add classes to wrap output of algorithms
Change MCMC and SMC to output MCMCOutput and SMCOutput respectively
Gather particles (and weights) prior to contructing SMCOutput block
Compare samples and weights for equality
Needed for unit/regression testing
If values not given, assume equal weights
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Diagnostics output
1 participant