786ab8c4d7ee758f80d57e65582e609d-AuthorFeedback.pdf

We would like to thank the reviewers for taking the time to carefully read, evaluate, and give feedback on our submission. "[T]his paper ... assumes that the feature map is regular (Assumption 3.1)... In particular, this gives us the flexibility of encoding many "inductive biases" into the architecture since only the two Therefore, Theorem 3.3 implies that if dropout is used to improve "One can hope that something as simple as the softmax function ... does not spoil It is not surprising that the softmax function preserve's the ability for an architecture Similar issues arise with the other mentioned examples and we would be happy to add a brief discussion outlining each.