On the Saturation Effect of Kernel Ridge Regression

Yicheng Li; Haobo Zhang; Qian Lin

doi:10.48550/arxiv.2405.09362

ICLR2023顶会

On the Saturation Effect of Kernel Ridge Regression

Yicheng Li, Haobo Zhang, Qian Lin

arXiv DOI 出版方

2023年份

2被引次数

16顶会引用

摘要

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.