tensorflow / tensorflow/probability
Independent logprob, per component return
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
is there the possibility to receive the logprob per component for an independent distribution?
I am using an IndependentNormal layer and want to calculate the log probability of the returned distribution for a drawn sample. The log probability seems to return the log of the product of each component or rather is summing the logs of each component at the end. However, I need the logprob of each component. Am I missing any argument to force neglect the summing over the last dimension?
Cheers
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 IndependentNormal entry point and its log probability behavior, then inspect the related distribution tests if available. Determine whether per-component log probabilities can be exposed without the final reduction; done means the requested behavior is supported or its limitation is clearly documented and tested.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100