tensorflow / tensorflow/probability
Provide seed to DenseReparameterization layer
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
I use DenseReparameterization for the transition function of a simple state-space model. To sample posterior sequences, I need to auto-regressively apply the layer to its own output inside of a symbolic loop. However, the samples are not consistent because the layer uses a different weight matrix at each iteration of the loop. Is it possible or are there plans to pass the seed into layer(inputs, seed=0) in order to sample consistent sequences?
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
No files, tests, or entry points are identified in the issue. Start by locating DenseReparameterization and its sampling path, then determine how a supplied seed should behave inside a symbolic loop. Done means the layer accepts the requested seed and produces consistent autoregressive samples, with tests covering that behavior.
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
- Mostly clear
- Newbie friendliness
- 25/100