tensorflow / tensorflow/probability

Independent logprob, per component return

Open
#982 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

layers
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

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 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.