probml / probml/dynamax

implement unscented particle filter using dynamax and blackjax

Open
#272 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

help wanted
Dominant language
Python
Stars
1k
Forks
114
Avg merge
19h 14m
Merged PRs (30d)
1

Description

Use EKF and/or UKF from dynamax as proposal distributions for sequential monte carlo from Blackjax to implement approximate inference in nonlinear Gaussian SSMsM. For details, see sec 13.3.2 of https://probml.github.io/pml-book/book2.html

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 section 13.3.2 of the referenced Probabilistic Machine Learning book, then review the existing EKF and UKF implementations in Dynamax and BlackJAX's sequential Monte Carlo API. Done means implementing approximate inference for nonlinear Gaussian state-space models using Dynamax EKF and/or UKF proposal distributions with BlackJAX.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.