Skip to main content
Share Your Experience: Take the 2024 Developer Survey

New answers tagged

0 votes

How to find an argument of a NN function(which returns a distribution) to minimize a KL divergence?

Since you made no assumption on what $q$ is, the problem is untractable If you assume $q$ to be Gaussian, it's easy to prove that the KL distance is minimized when you have $\mu_{f(s)}, \sigma_{f(s)}$ ...
Alberto's user avatar
  • 2,153

Top 50 recent answers are included