arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1306.2607cs.ITmath.IT
收藏

Fisher信息测度的一个下界

A Lower Bound for the Fisher Information Measure

Manuel Stein, Amine Mezghani, Josef A. Nossek

摘要:

研究了一般参数概率系统Fisher信息测度绝对值的近似确定问题。有可用的第一和第二时刻的系统输出的参数形式,它示出的信息测量可以从下面通过替换原系统的高斯系统具有等效的时刻有界。所提出的技术被应用到一个系统的实际重要性和潜在的质量的界限证明。

英文摘要:

The problem how to approximately determine the absolute value of the Fisher information measure for a general parametric probabilistic system is considered. Having available the first and second moment of the system output in a parametric form, it is shown that the information measure can be bounded from below through a replacement of the original system by a Gaussian system with equivalent moments. The presented technique is applied to a system of practical importance and the potential quality of the bound is demonstrated.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑