Regularized semi-supervised least squares regression with dependent samples

Hongzhi Tong, Kwok Po NG

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we study regularized semi-supervised least squares regression with dependent samples. We analyze the regularized algorithm based on reproducing kernel Hilbert spaces, and show, with the use of unlabelled data that the regularized least squares algorithm can achieve the nearly minimax optimal learning rate with a logarithmic term for dependent samples. Our new results are better than existing results in the literature.

Original languageEnglish
Pages (from-to)1347-1360
Number of pages14
JournalCommunications in Mathematical Sciences
Volume16
Issue number5
DOIs
Publication statusPublished - 2018

Scopus Subject Areas

  • Mathematics(all)
  • Applied Mathematics

User-Defined Keywords

  • Least squares regression
  • Non-iid sampling
  • Regularization
  • Semi-supervised learning

Fingerprint

Dive into the research topics of 'Regularized semi-supervised least squares regression with dependent samples'. Together they form a unique fingerprint.

Cite this