I'm using some bayesian hyperparameter optimization. I know how they works .

They always calculate the next values of the hyperparameter dependent on the result of former evaluations.

But what makes them bayesian? I know the bayesian theorem is:

p(A|B) = (P(B|A) * P(A)) / P(B)

What is the connection between this formula an the process of bayesian hyperparameter optimization? Is it just that the probability of a hyperparameter value depends on condition (former evaluations) we consider as relevant for the event?

Thanks for helping!

  • $\begingroup$ The previous evaluations indeed act as defining the prior distribution. $\endgroup$ – usεr11852 Jun 30 '19 at 11:07

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.