S. Mei, and A. Montanari. (2019)cite arxiv:1908.05355Comment: We added two sections in version 3. One section provides the precise asymptotics of the training error. The other section describes a Gaussian covariate model, which gives the same asymptotic test error as the random features model.
S. Kamath, A. Orlitsky, D. Pichapati, and A. Suresh. Proceedings of The 28th Conference on Learning Theory, volume 40 of Proceedings of Machine Learning Research, page 1066--1100. Paris, France, PMLR, (03--06 Jul 2015)