English

On the Saturation Effect of Kernel Ridge Regression

Machine Learning 2024-05-29 v2 Machine Learning

Abstract

The saturation effect refers to the phenomenon that the kernel ridge regression (KRR) fails to achieve the information theoretical lower bound when the smoothness of the underground truth function exceeds certain level. The saturation effect has been widely observed in practices and a saturation lower bound of KRR has been conjectured for decades. In this paper, we provide a proof of this long-standing conjecture.

Cite

@article{arxiv.2405.09362,
  title  = {On the Saturation Effect of Kernel Ridge Regression},
  author = {Yicheng Li and Haobo Zhang and Qian Lin},
  journal= {arXiv preprint arXiv:2405.09362},
  year   = {2024}
}

Comments

ICLR 2023; Minor errors are corrected in this version

R2 v1 2026-06-28T16:28:13.800Z