-
Notifications
You must be signed in to change notification settings - Fork 87
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Missing Scalar Rules #100
Comments
Arguably, we want to replace anywhere the derivative is not defined with |
No guarantees:
Poly gamma seems to be already implemented |
@freemin7 if you wouldn't mind turning the above into a PR, that would be fantastic. |
I will turn it into a PR |
See #173 Clamp's derivative is undefined at high and low and i had to do a rewrite of my code to satisfy the macro gods. |
It is zero? It is undefined at the edge but we can just chose it to be zero there which is correct enough for anything using subgradients.
You do not have to use the macro. |
We have a lot of scalar rules
A few I know are still missing
ldexp
(WolframAlpha partials)clamp
see https://discuss.pytorch.org/t/torch-round-gradient/28628/3polygamma
Zero
everywhere it is differentiableIdk if we want to close over the point gsps. (We do that for
abs
)round
see https://discuss.pytorch.org/t/torch-round-gradient/28628/3floor
ceil
The text was updated successfully, but these errors were encountered: