English

Optimal Rate of Kernel Regression in Large Dimensions

Machine Learning 2024-07-01 v2 Machine Learning Statistics Theory Statistics Theory

Abstract

We perform a study on kernel regression for large-dimensional data (where the sample size nn is polynomially depending on the dimension dd of the samples, i.e., ndγn\asymp d^{\gamma} for some γ>0\gamma >0 ). We first build a general tool to characterize the upper bound and the minimax lower bound of kernel regression for large dimensional data through the Mendelson complexity εn2\varepsilon_{n}^{2} and the metric entropy εˉn2\bar{\varepsilon}_{n}^{2} respectively. When the target function falls into the RKHS associated with a (general) inner product model defined on Sd\mathbb{S}^{d}, we utilize the new tool to show that the minimax rate of the excess risk of kernel regression is n1/2n^{-1/2} when ndγn\asymp d^{\gamma} for γ=2,4,6,8,\gamma =2, 4, 6, 8, \cdots. We then further determine the optimal rate of the excess risk of kernel regression for all the γ>0\gamma>0 and find that the curve of optimal rate varying along γ\gamma exhibits several new phenomena including the multiple descent behavior and the periodic plateau behavior. As an application, For the neural tangent kernel (NTK), we also provide a similar explicit description of the curve of optimal rate. As a direct corollary, we know these claims hold for wide neural networks as well.

Keywords

Cite

@article{arxiv.2309.04268,
  title  = {Optimal Rate of Kernel Regression in Large Dimensions},
  author = {Weihao Lu and Haobo Zhang and Yicheng Li and Manyun Xu and Qian Lin},
  journal= {arXiv preprint arXiv:2309.04268},
  year   = {2024}
}
R2 v1 2026-06-28T12:16:08.629Z