关于稀疏二次型的高阶迷向条件和下界
On higher order isotropy conditions and lower bounds for sparse quadratic forms
摘要:
本研究的目的是对经验相容常数或经验限制特征值的下界作出贡献。这在压缩感知和$\ell_1$ -正则化估计器的理论中是重要的。令$X$是一个$n \times p$数据矩阵,其中行是$p$维随机变量的独立副本。令$\hat Σ:= X^T X / n$为内积矩阵。我们证明了二次型$u^T \hat Σu$的下界收敛到一个值,一致超过一组向量$u$与$u^T Σ_0 u $等于1和$\ell_1$ -范数最多$M$。这里$Σ_0 := {\bf E} \hat Σ$是我们假设存在的理论内积矩阵。要求常数$M$具有小的阶数$\sqrt {n / \log p}$。此外,我们假设$m$阶各向同性的一些$m >2$和次指数的尾巴或时刻的顺序$\log p$的$X$中的条目。因此,我们得到的经验相容常数收敛到其理论对应,并同样为经验限制本征值。如果数据矩阵$X$首先被规范化,使其列都具有相等的长度,我们得到下界假设只有各向同性和没有进一步的时刻条件的条目。的各向同性条件,以保持一定的鞅的情况。
英文摘要:
This study aims at contributing to lower bounds for empirical compatibility constants or empirical restricted eigenvalues. This is of importance in compressed sensing and theory for $\ell_1$-regularized estimators. Let $X$ be an $n \times p$ data matrix with rows being independent copies of a $p$-dimensional random variable. Let $\hat Σ:= X^T X / n$ be the inner product matrix. We show that the quadratic forms $u^T \hat Σu$ are lower bounded by a value converging to one, uniformly over the set of vectors $u$ with $u^T Σ_0 u $ equal to one and $\ell_1$-norm at most $M$. Here $Σ_0 := {\bf E} \hat Σ$ is the theoretical inner product matrix which we assume to exist. The constant $M$ is required to be of small order $\sqrt {n / \log p}$. We assume moreover $m$-th order isotropy for some $m >2$ and sub-exponential tails or moments up to order $\log p$ for the entries in $X$. As a consequence we obtain convergence of the empirical compatibility constant to its theoretical counterpart, and similarly for the empirical restricted eigenvalue. If the data matrix $X$ is first normalized so that its columns all have equal length we obtain lower bounds assuming only isotropy and no further moment conditions on its entries. The isotropy condition is shown to hold for certain martingale situations.
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。