This paper studies the inductive bias of neural tangent kernels (NTKs) which is important in understanding the dynamics of learning in neural networks. There is a strong consensus among the reviewers that this paper provides solid theoretical results which help advance the theoretical understanding of deep neural networks. I also think that the topic addressed in this paper would be of interest to people in the NeurIPS community and would help bridge the gap between deep learning and theory of kernel methods. Hence, I would recommend to accept the paper.