You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Currently the custom VJP implementation is restricting the code to reverse mode differentiation. Though this is by far the more common of the two modes, we should add support for forward mode auto-diff, though it is not entirely clear how.
The text was updated successfully, but these errors were encountered:
You should consider using a custom_jvp instead, though does not seem very common .
You can get the forward mode derivative's value with a reverse mode differentiation for free.
The only reason to implement a jvp is when you only want the forward grad and you have a strict performance constraint and you don't want to waste performance on the backward pass
Currently the custom VJP implementation is restricting the code to reverse mode differentiation. Though this is by far the more common of the two modes, we should add support for forward mode auto-diff, though it is not entirely clear how.
The text was updated successfully, but these errors were encountered: