arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0903.4062math.PR
收藏

基于经典和一般链方法的最小条件下MLE偏差的渐近指数界

Asymptotic exponential bounds for MLE deviation under minimal conditions via classical and generic chaining methods

E. Ostrovsky, E. Rogover

摘要:

在本文中,非渐近精确的指数估计(在最小条件下)的尾部的偏差的MLE分布在所谓的自然条款:自然函数,自然距离,度量熵,巴拿赫空间的随机变量,对比功能,优化措施,或同样,一般的链接。

英文摘要:

In this paper non-asymptotic exact exponential estimates are derived (under minimal conditions) for the tail of deviation of the MLE distribution in the so-called natural terms: natural function, natural distance, metric entropy, Banach spaces of random variables, contrast function, majorizing measures or, equally, generic chaining.

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。

↑