Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
tf.igamma (lower regularized incomplete Gamma function) returns the incorrect derivative #17995
Describe the problem
This is probably very low down on the list of things to fix, but I wanted to highlight it since I spent something like 5 hours trying to understand why my model wasn't converging. I was fitting a Gamma distribution, and deep into the code it turns out that
I suspect the derivative wrt
My workaround ended up being not fitting
Filing this issue mostly in the hope that anyone in the future doesn't waste the same amount of time that I spent.
Source code / logs
Thank you for your post. We noticed you have not filled out the following field in the issue template. Could you update them if they are relevant in your case, or leave them as N/A? Thanks.
I was facing the same issue. The derivative wrt a is indeed not implemented: https://github.com/tensorflow/tensorflow/blob/d8f9538ab48e3c677aaf532769d29bc29a05b76e/tensorflow/python/ops/math_grad.py