NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:3292
Title:Intrinsic dimension of data representations in deep neural networks


		
This paper received mixed reviews from reviewers. Two reviewers are fairly strongly in favor, and one reviewer is fairly strongly against. The rebuttal clarified some points, but there was still some concern about lack of theoretical insights. While theory is important for advancing our field, empirical results often precede theory. The paper is interesting and should be accepted. Please cite and discuss Ma et al paper in camera ready.