A collaborative training algorithm for distributed learning

Research output: Contribution to journalArticle

82 Scopus citations

Abstract

In this paper, an algorithm is developed for collaboratively training networks of kernel-linear least-squares regression estimators. The algorithm is shown to distributively solve a relaxation of the classical centralized least-squares regression problem. A statistical analysis shows that the generalization error afforded agents by the collaborative training algorithm can be bounded in terms of the relationship between the network topology and the representational capacity of the relevant reproducing kernel Hilbert space. Numerical experiments suggest that the algorithm is effective at reducing noise. The algorithm is relevant to the problem of distributed learning in wireless sensor networks by virtue of its exploitation of local communication. Several new questions for statistical learning theory are proposed.

Original languageEnglish (US)
Pages (from-to)1856-1871
Number of pages16
JournalIEEE Transactions on Information Theory
Volume55
Issue number4
DOIs
StatePublished - Apr 16 2009

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Keywords

  • Collaboration
  • Distributed learning
  • Empirical risk minimization
  • Kernel methods
  • Learning
  • Nonparametric
  • Sensor networks

Fingerprint Dive into the research topics of 'A collaborative training algorithm for distributed learning'. Together they form a unique fingerprint.

  • Cite this