arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1001.4298cs.ITcond-mat.dis-nnmath.IT
收藏

一种典型压缩感知重构极限的统计力学分析

Statistical Mechanical Analysis of a Typical Reconstruction Limit of Compressed Sensing

Yoshiyuki Kabashima, Tadashi Wadayama, Toshiyuki Tanaka

摘要:

我们使用统计力学的复制方法来检查一个典型的性能正确重建$N$维稀疏向量$bx=(x_i)$从其线性变换$by=bF bx$的$P$维数的基础上最小化的$L_p$ -范数$||bx||_p= lim_{epsilon to +0} sum_{i=1}^N |x_i|^{p+epsilon}$。我们的重建性能的关键关系的成功重建之间的比率$alpha=P/N$和密度$rho$的非零元素在$bx$在极限$P,,N to infty$,同时保持$alpha sim O(1)$,并允许渐近可忽略的重建误差。我们发现,关键关系$alpha_c(rho)$普遍持有,只要$bF^{rm T}bF$可以渐近地由旋转不变的随机矩阵合奏和$bF bF^{rm T}$是典型的满秩。这支持了Donoho和Tanner观察到的批判关系的普遍性。横河《社会科学院学报》,第一卷~第367页~ 4273- 4293,2009; arXiv:0807.3590)。

英文摘要:

We use the replica method of statistical mechanics to examine a typical performance of correctly reconstructing $N$-dimensional sparse vector $bx=(x_i)$ from its linear transformation $by=bF bx$ of $P$ dimensions on the basis of minimization of the $L_p$-norm $||bx||_p= lim_{epsilon to +0} sum_{i=1}^N |x_i|^{p+epsilon}$. We characterize the reconstruction performance by the critical relation of the successful reconstruction between the ratio $alpha=P/N$ and the density $rho$ of non-zero elements in $bx$ in the limit $P,,N to infty$ while keeping $alpha sim O(1)$ and allowing asymptotically negligible reconstruction errors. We show that the critical relation $alpha_c(rho)$ holds universally as long as $bF^{rm T}bF$ can be characterized asymptotically by a rotationally invariant random matrix ensemble and $bF bF^{rm T}$ is typically of full rank. This supports the universality of the critical relation observed by Donoho and Tanner ({em Phil. Trans. R. Soc. A}, vol.~367, pp.~4273--4293, 2009; arXiv: 0807.3590) for various ensembles of compression matrices.

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。

↑