跳到主要导航 跳到搜索 跳到主要内容

Online Gradient Descent for Kernel-Based Maximum Correntropy Criterion

  • Baobin Wang
  • , Ting Hu*
  • *此作品的通讯作者
  • South Central Minzu University

科研成果: 期刊稿件 › 论文 › 同行评审

5 引用 (Scopus)

摘要

In the framework of statistical learning, we study the online gradient descent algorithm generated by the correntropy-induced losses in Reproducing kernel Hilbert spaces (RKHS). As a generalized correlation measurement, correntropy has been widely applied in practice, owing to its prominent merits on robustness. Although the online gradient descent method is an efficient way to deal with the maximum correntropy criterion (MCC) in non-parameter estimation, there has been no consistency in analysis or rigorous error bounds. We provide a theoretical understanding of the online algorithm for MCC, and show that, with a suitable chosen scaling parameter, its convergence rate can be min-max optimal (up to a logarithmic factor) in the regression analysis. Our results show that the scaling parameter plays an essential role in both robustness and consistency.
源语言英语
期刊论文编号644
页数13
期刊ENTROPY
卷21
期7
DOI
出版状态已出版 - 7月 2019

基金资助

The work described in this paper is partially supported by National Natural Science Foundation of China [Nos. 11671307 and 11571078], Natural Science Foundation of Hubei Province in China [No. 2017CFB523] and the Fundamental Research Funds for the Central Universities, South-Central University for Nationalities [No. CZY18033].

关键词

  • correntropy
  • maximum correntropy criterion
  • online algorithm
  • robustness
  • reproducing kernel Hilbert spaces

收录

  • Scopus
  • SCIE

学术指纹

探究 'Online Gradient Descent for Kernel-Based Maximum Correntropy Criterion' 的科研主题。它们共同构成独一无二的学术指纹。

引用此