Distributed kernel gradient descent algorithm for minimum error entropy principle

Distributed learning based on the divide and conquer approach is a powerful tool for big data processing. We introduce a distributed kernel gradient descent algorithm for the minimum error entropy principle and analyze its convergence. We show that the L2 error decays at a minimax optimal rate under...

Full description

Saved in:
Bibliographic Details
Published inApplied and computational harmonic analysis Vol. 49; no. 1; pp. 229 - 256
Main Authors Hu, Ting, Wu, Qiang, Zhou, Ding-Xuan
Format Journal Article
LanguageEnglish
Published Elsevier Inc 01.07.2020
Subjects
Distributed learning
Gradient descent algorithm
Kernel method
Minimum error entropy
Distributed learning
Gradient descent algorithm
Minimum error entropy
Kernel method
Online AccessGet full text
ISSN1063-5203
1096-603X
DOI10.1016/j.acha.2019.01.002

Cover

More Information
Summary:Distributed learning based on the divide and conquer approach is a powerful tool for big data processing. We introduce a distributed kernel gradient descent algorithm for the minimum error entropy principle and analyze its convergence. We show that the L2 error decays at a minimax optimal rate under some mild conditions. As a tool we establish some concentration inequalities for U-statistics which play pivotal roles in our error analysis.
ISSN:1063-5203
1096-603X
DOI:10.1016/j.acha.2019.01.002