误分类概率的精确上下界
统计理论
2018-02-12 v4 机器学习
概率论
统计理论
摘要
针对有限个类别，依据各类别上子分布之间差异的全变差范数，得到了最佳可能误分类概率的精确下界与上界。将这些界与 Feder 和 Merhav 依据条件熵得到的精确界进行了比较。
引用
@article{arxiv.1712.00812,
title = {Exact upper and lower bounds on the misclassification probability},
author = {Iosif Pinelis},
journal= {arXiv preprint arXiv:1712.00812},
year = {2018}
}
备注
Version 3: exact upper bounds are added; results are compared with ones by Feder and Merhav. Version 4: additional discussion presented