Is it specified anywhere what the backend is for the Bayesian optimization related functionality in Mathematica v11? I'm specifically referring to the Bayesian* functions like BayesianMinimization. Are they based on an open-source package like Spearmint, or on a brand new implementation? For example the neural network functionality is based on MXNet, but I couldn't find any information in the docs about the backend that's being used for Bayesian optimization.

  • 1
    $\begingroup$ it seems to use the same implementation of Gaussian Processes as is used by the Predict/Classify framework. this suggests it's probably a brand new implementation. $\endgroup$ Jan 17, 2018 at 2:35


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.