dfm / dfm/tinygp

quasiseparable kernel convolution

Open
#259 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
349
Forks
35
Avg merge
2d 2h
Merged PRs (30d)
1

Description

Hi @dfm et al.,

tinygp is solving lots of my problems, thanks for your hard work.

One feature that's in celerite2 but not tinygp is TermConvolution (source), which convolves a quasiseparable kernel with an observation duration.

What would the path look like to implement its equivalent in tinygp? I'd be happy to make a PR if I had some pointers on where to start.

Thanks!

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 by reading celerite2/jax/terms.py at the referenced TermConvolution implementation and then locate tinygp’s quasiseparable kernel code. Determine how an equivalent observation-duration convolution would fit tinygp; done means tinygp supports the requested equivalent feature with behavior matching the celerite2 reference.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.