arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.0093cs.ITmath.IT
收藏

通过$F$最小化实现稀疏恢复的鲁棒性:拓扑观点

Robustness of Sparse Recovery via $F$-minimization: A Topological Viewpoint

Jingbo Liu, Jian Jin, Yuantao Gu

摘要:

压缩感知的一个最近的趋势是考虑非凸优化技术的稀疏恢复。$F$ -最小化的重要情况已经变得特别感兴趣,对于该情况,在无噪声设置中的精确重构条件(ERC)可以精确地由零空间属性(NSP)表征。然而,很少有工作已经做了关于其鲁棒重建条件(RRC)在噪声环境中。我们把测量矩阵的零空间看作Grassmann流形上的一个点,然后研究了ERC集和RRC集之间的关系,分别记为$Ω_J$和$Ω_J^r$.它表明,$Ω_J^r$是内部的$Ω_J$,从以前的结果等价的ERC和RRC的$\ell_p$ -最小化容易遵循的特殊情况。此外,当$F$是非减的,它表明,$\overlineΩ_J\setminus\interior(Ω_J)$是一个集的措施零和第一类。因此,如果测量矩阵$\mathbf{A}$根据连续分布随机生成,则ERC和RRC的概率相同。量化地,如果零空间$\mathcal{N}(\bf A)$位于$Ω_J$的“$d$ -内部”,则RRC将满足鲁棒性常数$C=\frac{2+2d}{dσ_{\min}(\mathbf{A}^{\top})}$ ;并且相反地,如果RRC与$C=\frac{2-2d}{dσ_{\max}(\mathbf{A}^{\top})}$成立,则$\mathcal{N}(\bf A)$必须位于$Ω_J$的$d$ -内部。我们还提出了几个规则比较不同的成本函数的性能。最后,这些结果被资本化,以获得可实现的权衡之间的测量速率和鲁棒性的帮助下,戈登的逃逸通过网格定理或NSP和限制特征值条件之间的连接。

英文摘要:

A recent trend in compressed sensing is to consider non-convex optimization techniques for sparse recovery. The important case of $F$-minimization has become of particular interest, for which the exact reconstruction condition (ERC) in the noiseless setting can be precisely characterized by the null space property (NSP). However, little work has been done concerning its robust reconstruction condition (RRC) in the noisy setting. We look at the null space of the measurement matrix as a point on the Grassmann manifold, and then study the relation between the ERC and RRC sets, denoted as $Ω_J$ and $Ω_J^r$, respectively. It is shown that $Ω_J^r$ is the interior of $Ω_J$, from which a previous result of the equivalence of ERC and RRC for $\ell_p$-minimization follows easily as a special case. Moreover, when $F$ is non-decreasing, it is shown that $\overlineΩ_J\setminus\interior(Ω_J)$ is a set of measure zero and of the first category. As a consequence, the probabilities of ERC and RRC are the same if the measurement matrix $\mathbf{A}$ is randomly generated according to a continuous distribution. Quantitatively, if the null space $\mathcal{N}(\bf A)$ lies in the "$d$-interior" of $Ω_J$, then RRC will be satisfied with the robustness constant $C=\frac{2+2d}{dσ_{\min}(\mathbf{A}^{\top})}$; and conversely if RRC holds with $C=\frac{2-2d}{dσ_{\max}(\mathbf{A}^{\top})}$, then $\mathcal{N}(\bf A)$ must lie in $d$-interior of $Ω_J$. We also present several rules for comparing the performances of different cost functions. Finally, these results are capitalized to derive achievable tradeoffs between the measurement rate and robustness with the aid of Gordon's escape through the mesh theorem or a connection between NSP and the restricted eigenvalue condition.

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。

↑