tensorflow / tensorflow/probability

Implement (folded) rank normalized R hat

Open
#709 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

Reference [3] in the potential_scale_reduction documentation recommends rank normalization (section 4.1) and folded rank normalization (section 4.2) for better assessing convergence in the presence of heavy tails.

I'd like to contribute implementing this. Would an extra argument in tfp.mcmc.potential_scale_reduction in the spirit of split_chains be a good choice?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at the tfp.mcmc.potential_scale_reduction API and read sections 4.1 and 4.2 of Reference [3] in the linked documentation. Clarify with maintainers whether rank normalization and folded rank normalization belong behind an extra argument like split_chains; done means the agreed API supports both convergence assessments.

Written by the indexing model from the issue text.

Assessment

Tech stack
tensorflow
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.