论文标题
不变统计模型的下限，并应用于主成分分析
Lower bounds for invariant statistical models with applications to principal component analysis
论文作者
论文摘要
本文为估计协方差操作员的特征空间而产生了非吞噬信息不平等。这些结果概括了峰值协方差模型的先前下限，它们表明，具有衰减特征值的模型的最新上限很清晰。证明依赖于基于群体不变性参数的下边界技术，这些技术也可以处理其他各种统计模型。
This paper develops nonasymptotic information inequalities for the estimation of the eigenspaces of a covariance operator. These results generalize previous lower bounds for the spiked covariance model, and they show that recent upper bounds for models with decaying eigenvalues are sharp. The proof relies on lower bound techniques based on group invariance arguments which can also deal with a variety of other statistical models.
