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?


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.