"Optimal-Partitioning Inequalities in Classification and Multi-Hypothes" by Theodore P. Hill and Y. L. Tong
 

Abstract

Optimal-partitioning and minimax risk inequalities are obtained for the classification and multi-hypotheses testing problems. Best possible bounds are derived for the minimax risk for location parameter families, based on the tail concentrations and Levy concentrations of the distributions. Special attention is given to continuous distributions with the maximum likelihood ratio property and to symmetric unimodal continuous distributions. Bounds for general (including discontinuous) distributions are also obtained.

Disciplines

Mathematics

Plum Print visual indicator of research metrics
PlumX Metrics
  • Citations
    • Citation Indexes: 6
  • Usage
    • Downloads: 253
    • Abstract Views: 46
see details

Included in

Mathematics Commons

COinS
 

URL: https://digitalcommons.calpoly.edu/rgp_rsr/44