Mixture of Gaussian Processes Based on Bayesian Optimization

This paper gives a detailed introduction of implementing mixture Gaussian process (MGP) model and develops its application for Bayesian optimization (BayesOpt). The also techniques MGP in finding components introduced an alternative gating network based on the Dirichlet distributions. BayesOpt using resultant significantly outperforms one regression terms efficiency test tuning hyperparameters common machine learning algorithms. indicates success methods, implying promising future wider it.