Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper under review'Predictive Entropy Search for Efficient Global Optimization of Black-box Functions' presents an approach for Bayesian optimization that measures entropy in the posterior predictive distribution. The authors present a method named Predictive Entropy Search (PES) that is derived by a reparameterization of the expected information gain based on the symmetry of mutual information. The authors describe the posterior sampling, predictive entropy approximation and hyper-parameter learning steps of PES. The advantages of the proposed method are that it is more efficient and accurate than alternatives and that it allows to handle the hyper-parameters in a fully Bayesian way.