On the Saturation Effect of Kernel Ridge Regression

Yicheng Li, Haobo Zhang, Qian Lin
5/15/2024
stat.MLcs.LG

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

On the Saturation Effects of Spectral Algorithms in Large Dimensions

86% match2025

Optimal Rates and Saturation for Noiseless Kernel Ridge Regression

84% match2024

Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions

82% match2024

Learning Curves of Stochastic Gradient Descent in Kernel Regression

82% match2026

Kernel Ridge Regression Inference

82% match2023

A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression

81% match2024

Cite this paper

@article{li2024saturation,
  title  = {On the Saturation Effect of Kernel Ridge Regression},
  author = {Yicheng Li and Haobo Zhang and Qian Lin},
  year   = {2024},
  eprint = {2405.09362},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.09362v2},
  journal = {ICLR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.09362.svg)](https://codeofpaper.com/paper/2405.09362)

Discussion