NeurIPS 2020

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

Meta Review

After the thorough discussion among the reviewers, there is a consensus that this is a good paper that warrants acceptance. There were some skepticisms in the initial reviews, but the authors have provided a rebuttal which addressed most of the major concerns. The reviewers have updated their reviews/scores accordingly. Hence, the paper is accepted as a poster. Based on my own judgement, the presentation of this paper should be improved in the camera-ready version. Moreover, please, include (at least in the appendix) the additional experiment result that you did to verify/proof-check your theorems. On top of that, the reviewers have already summarized their suggestion for changes that will help improve the paper further. Please, take them into consideration when preparing the camera-ready version of the paper.