Ridgeless Regression with Random Features

Jian Li; Yong Liu; Yingying Zhang

IJCAI 2022poster3 citations

Ridgeless Regression with Random Features

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.

Machine Learning: Learning TheoryMachine Learning: Kernel Methods

BibTeX

@inproceedings{ijcai2022p445,
  title     = {Ridgeless Regression with Random Features},
  author    = {Li, Jian and Liu, Yong and Zhang, Yingying},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {3208--3214},
  year      = {2022},
  month     = {7},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2022/445},
  url       = {https://doi.org/10.24963/ijcai.2022/445},
}