arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1107.5481math.PRmath.STstat.TH
收藏

高维高斯矩阵经验投影的精度

Accuracy of empirical projections of high-dimensional Gaussian matrices

Angelika Rohde

摘要:

设$X=C+\mathrm{E}$具有一个确定性矩阵$C\in\R^{M\times M}$和$\mathrm{E}$,其中某个中心高斯$M\times M$ -矩阵的元素与方差$σ^2$无关.在目前的工作中,降秩投影的$X$的精度进行了研究。非渐近的普遍的上界和下界的推导,和有利的和不利的原型矩阵$C$的近似精度的特点。该方法不涉及分析扰动理论的线性算子,并允许在奇异值谱的多重性。我们的主要结果是一些一般的非渐近上界的逼近精度,其中明确涉及奇异值的$C$,并被证明是尖锐的$C$在各种制度。结果伴随着不同的假设下的下限。统计估计问题的后果,特别是在最近的低秩矩阵恢复领域,进行了讨论。

英文摘要:

Let $X=C+\mathrm{E}$ with a deterministic matrix $C\in\R^{M\times M}$ and $\mathrm{E}$ some centered Gaussian $M\times M$-matrix whose entries are independent with variance $σ^2$. In the present work, the accuracy of reduced-rank projections of $X$ is studied. Non-asymptotic universal upper and lower bounds are derived, and favorable and unfavorable prototypes of matrices $C$ in terms of the accuracy of approximation are characterized. The approach does not involve analytic perturbation theory of linear operators and allows for multiplicities in the singular value spectrum. Our main result is some general non-asymptotic upper bound on the accuracy of approximation which involves explicitly the singular values of $C$, and which is shown to be sharp in various regimes of $C$. The results are accompanied by lower bounds under diverse assumptions. Consequences on statistical estimation problems, in particular in the recent area of low-rank matrix recovery, are discussed.

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。

↑