1b742ae215adf18b75449c6e272fd92d-AuthorFeedback.pdf

We thank all the reviewers for their time and effort in providing feedback. For clarity, we would like to reiterate the goal and motivation of the paper. Ingeneral, wedonothaveaccess14 to the target network, but only to the labeled training data. AsoptimizingReLU16 neural network is itself NP-Hard in general, we expect all algorithms to be inefficient in the worst case. Thus, the approximated network achieved 97.17% test set accuracy with 44.69% sparsity.27