tensorflow / tensorflow/probability
tf.math.betainc is missing gradients
Open
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'm trying to fit a NegativeBinomial, but its cdf seems to be missing some gradients:
count = tf.compat.v1.get_variable("count", shape=())
logit = tf.compat.v1.get_variable("logit", shape=())
value = tf.compat.v1.get_variable("value", shape=())
cdf = tfpd.NegativeBinomial(total_count=count, logits=logit).cdf(value)
print(tf.gradients(cdf, [count])) # Prints `None`.
print(tf.gradients(cdf, [logit])) # Works.
print(tf.gradients(cdf, [value])) # Prints `None`.
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
Reproduce the example with tfp.NegativeBinomial.cdf and tf.gradients, then trace the missing gradient through tf.math.betainc. Confirm that gradients with respect to count and value are no longer None while the existing logit gradient continues to work.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100