How rotational invariance of common kernels prevents generalization in high dimensions

Abstract

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 kernel regression under certain assumptions on the ground truth function and the distribution of the input data. In this paper, we show that the rotational invariance property of commonly studied kernels (such as RBF, inner product kernels and fully-connected NTK of any depth) induces a bias towards low-degree polynomials in high dimensions. Our result implies a lower bound on the generalization error for a wide range of distributions and various choices of the scaling for kernels with different eigenvalue decays. This lower bound suggests that general consistency results for kernel ridge regression in high dimensions require a more refined analysis that depends on the structure of the kernel beyond its eigenvalue decay.

References in corpus (9)

• The generalization error of random features regression: Precise asymptotics and double descent curve
• Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
• Consistency and robustness of kernel-based regression in convex risk minimization
• When Do Neural Networks Outperform Kernel Methods?
• Does data interpolation contradict statistical optimality?
• Classification vs regression in overparameterized regimes: Does the loss function matter?
• Neural Kernels Without Tangents
• Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration
• Kernel regression in high dimensions: Refined analysis beyond double descent