Minimax risk inequalities for the location-parameter classification problem

JOURNAL OF MULTIVARIATE ANALYSIS

卷:66

Article

Allaart, PC

关键词: optimal-partitioning;    minimax risk;    classification;    partition range;    convexity theorem;    concentration function;    tail concentration;   

DOI  :  10.1006/jmva.1998.1748

来源: Elsevier

【 摘 要 】

Minimax risk inequalities are obtained for the location-parameter classification problem. For the classical single observation case with continuous distributions, best possible bounds are given in terms of their Levy concentration, establishing a conjecture of Hill and Tong (1989). In addition, sharp bounds for the minimax risk are derived for the multiple (i.i.d.) observations case, based on the tail concentration and the Levy concentration. Some Fairly sharp bounds for discontinuous distributions are also obtained. (C) 1998 Academic Press.

【 授权许可】

Free