Convergence analysis of distributed multi-penalty regularized pairwise learning

Ting Hu, Jun FAN, Dao Hong Xiang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

In this paper, we establish the error analysis for distributed pairwise learning with multi-penalty regularization, based on a divide-and-conquer strategy. We demonstrate with L2-error bound that the learning performance of this distributed learning scheme is as good as that of a single machine which could process the whole data. With semi-supervised data, we can relax the restriction of the number of local machines and enlarge the range of the target function to guarantee the optimal learning rate. As a concrete example, we show that the work in this paper can apply to the distributed pairwise learning algorithm with manifold regularization.

Original languageEnglish
Pages (from-to)109-127
Number of pages19
JournalAnalysis and Applications
Volume18
Issue number1
DOIs
Publication statusPublished - 1 Jan 2020

Scopus Subject Areas

  • Analysis
  • Applied Mathematics

User-Defined Keywords

  • distributed learning
  • multi-penalty regularization
  • Pairwise learning
  • reproducing kernel Hilbert space

Fingerprint

Dive into the research topics of 'Convergence analysis of distributed multi-penalty regularized pairwise learning'. Together they form a unique fingerprint.

Cite this