Timezone: »

 
Poster
How rotational invariance of common kernels prevents generalization in high dimensions
Konstantin Donhauser · Mingqi Wu · Fanny Yang

Thu Jul 22 09:00 PM -- 11:00 PM (PDT) @ Virtual
in Poster Session 6 »

Kernel ridge regression is well-known to achieve minimax optimal rates in low-dimensional settings. However, its behavior in high dimensions is much less understood. Recent work establishes consistency for high-dimensional kernel regression for a number of specific assumptions on the data distribution. In this paper, we show that in high dimensions, the rotational invariance property of commonly studied kernels (such as RBF, inner product kernels and fully-connected NTK of any depth) leads to inconsistent estimation unless the ground truth is a low-degree polynomial. Our lower bound on the generalization error holds for a wide range of distributions and kernels with different eigenvalue decays. This lower bound suggests that consistency results for kernel ridge regression in high dimensions generally require a more refined analysis that depends on the structure of the kernel beyond its eigenvalue decay.

Keywords: Statistical Learning Theory
[ Slides] 

Author Information

Konstantin Donhauser (ETH Zürich)
Mingqi Wu (ETH Zurich)
Fanny Yang (ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors