|
Abstract:
|
We study the risk of minimum-norm interpolants of data in a reproducing kernel hilbert space, where kernel is defined as a function of the inner product. Our upper bounds on the risk are of a multiple-descent shape for the various scalings of d=n^alpha, where alpha is in [0,1], for the input dimension d and sample size n. At the heart of our analysis is a study of spectral properties of the random kernel matrix restricted to a filtration of eigen-spaces of the population covariance operator. Since gradient flow on appropriately initialized wide neural networks converges to a minimum-norm interpolant, the analysis also yields estimation guarantees for these models.
|
