English

Ridgeless Regression with Random Features

Machine Learning 2023-08-30 v1 Information Theory math.IT Machine Learning

Abstract

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless regression with random features and stochastic gradient descent. We explore the effect of factors in the stochastic gradient and random features, respectively. Specifically, random features error exhibits the double-descent curve. Motivated by the theoretical findings, we propose a tunable kernel algorithm that optimizes the spectral density of kernel during training. Our work bridges the interpolation theory and practical algorithm.

Keywords

Cite

@article{arxiv.2205.00477,
  title  = {Ridgeless Regression with Random Features},
  author = {Jian Li and Yong Liu and Yingying Zhang},
  journal= {arXiv preprint arXiv:2205.00477},
  year   = {2023}
}

Comments

Accepted at IJCAI 2022

R2 v1 2026-06-24T11:03:55.221Z