8abfe8ac9ec214d68541fcb888c0b4c3-AuthorFeedback.pdf

We thank the reviewers for the positive reviews and valuable feedback. Then, we reply to other remarks. We will update the manuscript accordingly. The idea of the proof is to combine the PL-inequality in Lemma 4.1 NTK is not well defined. On the contrary, our paper just requires the first layer to be overparameterized (i.e., all the As noted by Rev. 3, if Thus, GD requires more iterations to converge to a global optimum.