tensorflow / tensorflow/probability
Feature Request: Gumbel Mixture Models
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
It is possible to construct reparameterizable mixture distributions by replacing the categorical distribution with a gumbel (relaxed categorical) distribution. The ability to use a relaxed one-hot categorical distribution in mixture or mixtureSameFamily would be potentially very useful.
Differentiable mixture distributions implemented in torch here:
https://github.com/nextBillyonair/DPM/blob/master/dpm/distributions/gumbel_mixture_model.py
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 reviewing the linked reference implementation at dpm/distributions/gumbel_mixture_model.py and the existing mixture and mixtureSameFamily entry points in TensorFlow Probability. Determine the intended relaxed one-hot categorical behavior and define tests that establish reparameterization and mixture usage before considering the feature complete.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100