TuringLang / TuringLang/EllipticalSliceSampling.jl
Potential interesting ESS improvement based on mixture of Gaussians
Nobody has claimed this yet.
- Dominant language
- Julia
- Stars
- 16
- Forks
- 7
- PR merge metrics
- No merged PRs in 30d
Description
The paper below proposes an interesting extension of ESS that handles models with non-Gaussian prior, and models with Gaussian priors but with informative likelihoods. The authors also motivate their algorithm for parallelisable implementation. If this work well in practice, it could be an interesting gradient-free alternative to the HMC/NUTS sampler for low to mid dimensional problems.
Nishihara, R., Murray, I., & Adams, R. P. (2014). Parallel MCMC with Generalized Elliptical Slice Sampling. Journal of Machine Learning Research: JMLR, 15(61), 2087–2112.
@imurray @robertnishihara
Contributor guide
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 cited paper on Parallel MCMC with Generalized Elliptical Slice Sampling and reviewing the existing elliptical slice sampling implementation. Clarify which algorithmic capabilities should be added, how they fit the current API, and what tests or examples would demonstrate that the improvement is complete.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100