2018

Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon

Rakhlin, Alexander, Zhai, Xiyu

Understand

We show that minimum-norm interpolation in the Reproducing Kernel Hilbert Space corresponding to the Laplace kernel is not consistent if input dimension is constant.

  • The lower bound holds for any choice of kernel bandwidth, even if selected based on data.
  • The result supports the empirical observation that minimum-norm interpolation (that is, exact fit to training data) in RKHS generalizes well for some high-dimensional datasets, but not for low-dimensional ones.

Built on

  • Introduction to Fourier analysis on Euclidean spaces (PMS-32)

    Elias M Stein and Guido Weiss · 1971

    Earlier work this paper cites.

  • A distribution-free theory of nonparametric regression

    László Györfi, Michael Kohler, Adam Krzyzak, and Harro Walk · 2006

    Earlier work this paper cites.

  • The spectrum of kernel random matrices

    Noureddine El Karoui · 2010

    Earlier work this paper cites.

Similar

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…