0
$\begingroup$

Does loss function need to be (at least locally) differentiable in order to be used in a model that support definition of loss function (e.g., xgboost, lstm, etc.)?

$\endgroup$
3
$\begingroup$

Loss function needs to be differentiable only if you are using optimization algorithm that needs the derivatives. Not every optimization algorithm does, but many do.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.