This is an interim version of our Electronic Legal Deposit Catalogue-eJournals and eBooks while we continue to recover from a cyber-attack.
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*This article is an updated version of: Liao Z, Couillet R and Mahoney M W 2020 A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent Advances in Neural Information Processing Systems vol 33, ed H Larochelle, M Ranzato, R Hadsell, M F Balcan and H Lin (New York: Curran Associates), pp 13939–50. (29th December 2021)
Record Type:
Journal Article
Title:
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*This article is an updated version of: Liao Z, Couillet R and Mahoney M W 2020 A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent Advances in Neural Information Processing Systems vol 33, ed H Larochelle, M Ranzato, R Hadsell, M F Balcan and H Lin (New York: Curran Associates), pp 13939–50. (29th December 2021)
Main Title:
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*This article is an updated version of: Liao Z, Couillet R and Mahoney M W 2020 A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent Advances in Neural Information Processing Systems vol 33, ed H Larochelle, M Ranzato, R Hadsell, M F Balcan and H Lin (New York: Curran Associates), pp 13939–50.
Abstract: This article characterizes the exact asymptotics of random Fourier feature (RFF) regression, in the realistic setting where the number of data samples n, their dimension p, and the dimension of feature space N are all large and comparable. In this regime, the random RFF Gram matrix no longer converges to the well-known limiting Gaussian kernel matrix (as it does when N → ∞ alone), but it still has a tractable behavior that is captured by our analysis. This analysis also provides accurate estimates of training and test regression errors for large n, p, N . Based on these estimates, a precise characterization of two qualitatively different phases of learning, including the phase transition between them, is provided; and the corresponding double descent test error curve is derived from this phase transition behavior. These results do not depend on strong assumptions on the data distribution, and they perfectly match empirical results on real-world data sets.