Expensive gradient evaluation for multivariate functions #267
jeanchristopheruel
started this conversation in
General
Replies: 1 comment 1 reply
-
Hi @jeanchristopheruel , this happens by design, and it is not an issue - this is how a forward mode automatic differentiation algorithm works. For gradient of a scalar function with many variables, a reverse algorithm, using |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Multivariate gradient evaluation is very expensive since the function is evaluated as many times as the number of variables.
Minimal example:
Beta Was this translation helpful? Give feedback.
All reactions