...
首页> 外文期刊>Information Theory, IEEE Transactions on >Bayesian Error-Based Sequences of Statistical Information Bounds
【24h】

Bayesian Error-Based Sequences of Statistical Information Bounds

机译:基于贝叶斯误差的统计信息边界序列

获取原文
获取原文并翻译 | 示例
           

摘要

The relation between statistical information and Bayesian error is sharpened by deriving finite sequences of upper and lower bounds on equivocation entropy (EE) in terms of the minimum probability of error (MPE) and related Bayesian quantities. The well-known Fano upper bound and Feder-Merhav lower bound on EE are tightened by including a succession of posterior probabilities starting at the largest, which directly controls the MPE, and proceeding to successively lower ones. A number of other interesting results are also derived, including a sequence of upper bounds on the MPE in terms of a previously introduced sequence of generalized posterior distributions. The tightness of the various bounds is numerically evaluated for a simple example.
机译:通过根据最小错误概率(MPE)和相关的贝叶斯量推导等值熵(EE)的上下限的有限序列,可以加强统计信息与贝叶斯误差之间的关系。 EE上著名的Fano上限和Feder-Merhav下限通过包括一系列从最大开始的后验概率来收紧,后者直接控制MPE,然后逐步降低。还得出了许多其他有趣的结果,包括根据先前引入的广义后验分布序列,MPE的上限序列。对于一个简单的例子,通过数值评估了各种边界的紧密度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号