Local Rademacher complexity bounds based on covering numbers

Yunwen Lei, Lixin Ding*, Yingzhou Bi

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

10 Citations (Scopus)

Abstract

This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate complexities with constraints on expected norms to the corresponding ones with constraints on empirical norms. This result is convenient to apply and could yield refined local Rademacher complexity bounds for function classes satisfying general entropy conditions. We demonstrate the power of our complexity bounds by applying them to simplify the derivation of effective generalization error bounds.

Original languageEnglish
Pages (from-to)320-330
Number of pages11
JournalNeurocomputing
Volume218
DOIs
Publication statusPublished - 19 Dec 2016

Scopus Subject Areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

User-Defined Keywords

  • Covering numbers
  • Learning theory
  • Local Rademacher complexity

Fingerprint

Dive into the research topics of 'Local Rademacher complexity bounds based on covering numbers'. Together they form a unique fingerprint.

Cite this