Sobolev norm inconsistency of kernel interpolation
By: Yunfei Yang
Potential Business Impact:
Makes computers learn better by understanding data patterns.
We study the consistency of minimum-norm interpolation in reproducing kernel Hilbert spaces corresponding to bounded kernels. Our main result give lower bounds for the generalization error of the kernel interpolation measured in a continuous scale of norms that interpolate between $L^2$ and the hypothesis space. These lower bounds imply that kernel interpolation is always inconsistent, when the smoothness index of the norm is larger than a constant that depends only on the embedding index of the hypothesis space and the decay rate of the eigenvalues.
Similar Papers
General superconvergence for kernel-based approximation
Numerical Analysis
Makes math guesses faster for smoother problems.
On the Convergence of Irregular Sampling in Reproducing Kernel Hilbert Spaces
Machine Learning (Stat)
Makes computer learning better with less data.
Optimal convergence rates for the finite element approximation of the Sobolev constant
Numerical Analysis
Finds best math shapes for complex problems.