arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1502.04977math.STmath.OCstat.TH
收藏

$\ell_2$ - LASSO的精密误差分析

Precise Error Analysis of the $\ell_2$-LASSO

Christos Thrampoulidis, Ashkan Panahi, Daniel Guo, Babak Hassibi

摘要:

在许多信号处理应用中出现的经典问题要求从欠定、噪声、线性测量$y=Ax_0+z\in R^m$重建未知的$k$ -稀疏信号$x_0\in R^n$。一种标准方法是求解以下凸程序$\hat x=\arg\min_x \|y-Ax\|_2 + λ\|x\|_1$,称为$\ell_2$ -LASSO。我们假设感测矩阵$A$和噪声向量$z$的条目是具有方差$1/m$和$σ^2$的独立同分布高斯。在大系统的极限时,问题的尺寸增长到无穷大,但在恒定的速率,我们\emph{precisely}特征的归一化平方误差$\|\hat x-x_0\|^2_2/σ^2$的限制行为。我们的数值例子验证了我们的理论预测。

英文摘要:

A classical problem that arises in numerous signal processing applications asks for the reconstruction of an unknown, $k$-sparse signal $x_0\in R^n$ from underdetermined, noisy, linear measurements $y=Ax_0+z\in R^m$. One standard approach is to solve the following convex program $\hat x=\arg\min_x \|y-Ax\|_2 + λ\|x\|_1$, which is known as the $\ell_2$-LASSO. We assume that the entries of the sensing matrix $A$ and of the noise vector $z$ are i.i.d Gaussian with variances $1/m$ and $σ^2$. In the large system limit when the problem dimensions grow to infinity, but in constant rates, we \emph{precisely} characterize the limiting behavior of the normalized squared-error $\|\hat x-x_0\|^2_2/σ^2$. Our numerical illustrations validate our theoretical predictions.

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。

↑