Publication Date

3-1997

Series Number

Preprint # - 1997-28

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.

Comments

This preprint was published as Yuhong Yand and Andrew Barron, " Information-Theoretic Determination of Minimax Rates of Convergence", The Annals of Statistics (1999): 1564-1599, doi: 10.1214/aos/1017939142.

Language

en

Share

COinS