Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem

Yunwen Lei, Lixin Ding

Research output: Contribution to journalLetterpeer-review

9 Citations (Scopus)

Abstract

Estimating the Rademacher chaos complexity of order two is important for understanding the performance of multikernel learning (MKL) machines. In this letter, we develop a novel entropy integral for Rademacher chaos complexities. As compared to the previous bounds, our result is much improved in that it introduces an adjustable parameter ε to prohibit the divergence of the involved integral. With the use of the iteration technique in Steinwart and Scovel (2007), we also apply our Rademacher chaos complexity bound to the MKL problems and improve existing learning rates.

Original languageEnglish
Pages (from-to)739-760
Number of pages22
JournalNeural Computation
Volume26
Issue number4
DOIs
Publication statusPublished - 1 Apr 2014
Externally publishedYes

Scopus Subject Areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem'. Together they form a unique fingerprint.

Cite this