The docs show the following options for BayesianMaximization's Method:
"MaxExpectedImprovement" maximize expected improvement over current best value "MaxImprovementProbability" maximize improvement probability over current best value
But what these mean I do not know. Typical methods for bayesian optimization are: TPE (tree of parzen estimators), Gaussian Processes, etc... I'd like to know more about the internals here.
BayesianMaximizationObject
, you can see that it uses Gaussian Process for prediction method. $\endgroup$