This paper proposes an extension to Bayesian optimization methods for model selection. A surrogate model for the dataset is added to the setup, which allows the optimization to take more information to account as data is collected over time. The reviewers generally thought this was an interesting approach and an important direction. The main debate focused on the significance of the synthetic results based on real data, and whether they can be expected to generalize. We think that the clear novelty and the positive results outweigh this weakness.