1
$\begingroup$

What kind of relationship is there between the KL (Kullback-Leibler) divergence, JS (Jensen-Shannon) divergence, and MMD (maximum mean discrepancy)?

I know that they all share a global minimum at $P=Q$ and that the JS divergence can be defined using two KL divergences. Are there any other known clear relationship among these three?

$\endgroup$

Your Answer

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

Browse other questions tagged or ask your own question.