Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

On the Saturation Effect of Kernel Ridge Regression

Yicheng Li · Haobo Zhang · Qian Lin

MH1-2-3-4 #141

Keywords: [ learning theory ] [ Reproducing kernel Hilbert space ] [ Kernel ridge regression ] [ Saturation effect ] [ Theory ]


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.

Chat is not available.