To Reviewer 1: 1 C1: The main weakness of this work is the complexity of the approach

R1: We do agree that our approach is complex and involves "multiple approximation steps". C2: On Park1, the NN "finds the global optimum after one query point"-- How is this significant... " First, the quality of the query point very much depends on the accuracy of the surrogate model. C3: Details about hyper-parameter selection; no liberty to choose a heldout dataset in practice. We optimized the hyper-parameters to minimize the average test error. We will supplement these details.