Information-theoretic determination of minimax rates of convergence

Yuhong Yang, Andrew Barron

Research output: Contribution to journalArticlepeer-review

198 Scopus citations

Abstract

We present some general results determining minimax bounds on statistical risk for density estimation based on certain information-theoretic considerations. These bounds depend only on metric entropy conditions and are used to identify the minimax rates of convergence.

Original languageEnglish (US)
Pages (from-to)1564-1599
Number of pages36
JournalAnnals of Statistics
Volume27
Issue number5
StatePublished - Oct 1999

Keywords

  • Density estimation
  • Kullback - Leibler distance
  • Metric entropy
  • Minimax risk

Fingerprint

Dive into the research topics of 'Information-theoretic determination of minimax rates of convergence'. Together they form a unique fingerprint.

Cite this