arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1012.0294math.PRmath.FA
收藏

经验协方差阵的收敛速率的精确界

Sharp bounds on the rate of convergence of the empirical covariance matrix

Radosław Adamczak, Alexander E. Litvak, Alain Pajor, Nicole Tomczak-Jaegermann

摘要:

设$X_1,..., X_N\in\R^n$为对数凹分布的独立中心随机向量,单位为协方差阵。我们表明,以压倒性的概率至少$1 - 3 \exp(-c\sqrt{n}\r)$一个有$ \sup_{x\in S^{n-1}} \Big|\frac{1/N}\sum_{i=1}^N (|<X_i, x>|^2 - \E|<X_i, x>|^2\r)\Big| \leq C \sqrt{\frac{n/N}},$,其中$C$是一个绝对的正常数。当线性形式$(<X_i,x>)_{i\leq N, x\in S^{n-1}}$和欧氏范数$(|X_i|/\sqrt n)_{i\leq N}$表现出一致的次指数衰减时,该结果在更一般的框架中是有效的。因此,如果$A$表示列为$(X_i)$的随机矩阵,则以压倒性的概率,$AA^\top$的极值奇异值$λ_{\rm min}$和$λ_{\rm max}$满足不等式$ 1 - C\sqrt{n/N} \le {λ_{\rm min}/N} \le \frac{λ_{\rm max}/N} \le 1 + C\sqrt{n/N} $,该不等式是已知用于i.i.d.条目

英文摘要:

Let $X_1,..., X_N\in\R^n$ be independent centered random vectors with log-concave distribution and with the identity as covariance matrix. We show that with overwhelming probability at least $1 - 3 \exp(-c\sqrt{n}\r)$ one has $ \sup_{x\in S^{n-1}} \Big|\frac{1/N}\sum_{i=1}^N (|<X_i, x>|^2 - \E|<X_i, x>|^2\r)\Big| \leq C \sqrt{\frac{n/N}},$ where $C$ is an absolute positive constant. This result is valid in a more general framework when the linear forms $(<X_i,x>)_{i\leq N, x\in S^{n-1}}$ and the Euclidean norms $(|X_i|/\sqrt n)_{i\leq N}$ exhibit uniformly a sub-exponential decay. As a consequence, if $A$ denotes the random matrix with columns $(X_i)$, then with overwhelming probability, the extremal singular values $λ_{\rm min}$ and $λ_{\rm max}$ of $AA^\top$ satisfy the inequalities $ 1 - C\sqrt{n/N} \le {λ_{\rm min}/N} \le \frac{λ_{\rm max}/N} \le 1 + C\sqrt{n/N} $ which is a quantitative version of Bai-Yin theorem \cite{BY} known for random matrices with i.i.d. entries.

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。

↑