NeurIPS 2020

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

Meta Review

The reviewers and I agree that this paper provides a solid analysis of random Fourier features in the high-dimensional regime and should be accepted. While there was some discussion regarding the improvement over Mei and Montanari (2019), I am confident that the technical novelty of this paper is more than sufficient to merit publication.