arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.06145math.STstat.TH
收藏

统计模型的稳健性

Robustness of statistical models

Andrea Loi, Stefano Matta

摘要:

由$(\tilde M, \tilde g, \tilde T)$诱导的光滑流形$M$上的统计结构$(g, T)$称为{ \em robust},如果在由$(\tilde M, \tilde g, \tilde T)$诱导的统计结构组成的精细$C^{\infty}$ -拓扑中存在$(g,T)$的开邻域。利用Nash-Gromov隐函数定理,我们证明了$N$足够大时,由${\R}^N$上的标准线性统计结构引起的$M$上的通用统计结构的鲁棒性。

英文摘要:

A statistical structure $(g, T)$ on a smooth manifold $M$ induced by $(\tilde M, \tilde g, \tilde T)$ is said to be {\em robust} if there exists an open neighborhood of $(g,T)$ in the fine $C^{\infty}$-topology consisting of statistical structures induced by $(\tilde M, \tilde g, \tilde T)$. Using Nash--Gromov implicit function theorem, we show robustness of the generic statistical structure induced on $M$ by the standard linear statistical structure on ${\R}^N$, for $N$ sufficiently large.

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。

↑