Consider re-writing innovation-based parameterizations of key stochastic processes as `numpyro.Distributions`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 29
- Forks
- 9
- Avg merge
- 9d 9h
- Merged PRs (30d)
- 8
Description
Avoiding the scan in log prob evaluation and using it only in forward sampling is a really nice feature of doing this as true
numpyroDistributions, rather than as PyRenewRandomVariables.Question: does this argue for reimplementing the innovation-based parameterizations in the same way? Do you expect performance implications?
Originally posted by @dylanhmorris in #828
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the discussion linked from PR #828, especially the comparison between NumPyro Distributions and PyRenew RandomVariables. Determine which innovation-based parameterizations are in scope and how forward sampling, log-probability evaluation, and performance should be assessed. Done means an agreed implementation direction and corresponding reimplementation or decision.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100