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 0903.2323math.PRmath.FA
收藏

对数凹系综中经验协方差阵收敛性的定量估计

Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles

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

摘要:

设$K$是$\R^n$中的各向同性凸体。给定$\eps>0$,经验协方差阵需要多少个均匀分布在$K$上的独立点$X_i$才能以压倒性的概率逼近直到$\eps$的恒等式?本文回答了Kannan、Lovasz和Simonovits提出的这个问题。更准确地说,让$X\in\R^n$是一个中心随机向量,具有对数凹分布,并具有协方差阵的身份。这种矢量$X$的一个例子是各向同性凸体中的随机点。我们证明了对于任何$\eps>0$,都存在$C(\eps)>0$,使得如果$N\sim C(\eps) n$和$(X_i)_{i\le N}$是i.i.d. $X$的拷贝,然后是概率大于$1-\exp(-c\sqrt n)$的$ \Big\|\frac{1}{N}\sum_{i=1}^N X_i\otimes X_i - \Id\Big\| \le ε, $。

英文摘要:

Let $K$ be an isotropic convex body in $\R^n$. Given $\eps>0$, how many independent points $X_i$ uniformly distributed on $K$ are needed for the empirical covariance matrix to approximate the identity up to $\eps$ with overwhelming probability? Our paper answers this question posed by Kannan, Lovasz and Simonovits. More precisely, let $X\in\R^n$ be a centered random vector with a log-concave distribution and with the identity as covariance matrix. An example of such a vector $X$ is a random point in an isotropic convex body. We show that for any $\eps>0$, there exists $C(\eps)>0$, such that if $N\sim C(\eps) n$ and $(X_i)_{i\le N}$ are i.i.d. copies of $X$, then $ \Big\|\frac{1}{N}\sum_{i=1}^N X_i\otimes X_i - \Id\Big\| \le ε, $ with probability larger than $1-\exp(-c\sqrt n)$.

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。

↑