arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1405.5887cs.ITmath.IT
收藏

ReProCS的性能保证--相关低秩矩阵条目案例

Performance Guarantees for ReProCS -- Correlated Low-Rank Matrix Entries Case

Jinchun Zhan, Namrata Vaswani, Chenlu Qiu

摘要:

在线或递归的鲁棒PCA可以被视为一个问题,即当新数据进入时,从$M_t:= S_t + L_t$动态地恢复稀疏向量$S_t$和密集向量$L_t$,$L_t$位于缓慢变化的低维子空间中。对于初始化,假设$L_0$所在的子空间的准确知识是可用的。在最近的工作中,Qiu等人提出并分析了一种新的解决方案,称为递归投影压缩感知或ReProCS。本文放宽了Qiu等人结果的一个限制性假设。他们的工作要求$L_t$在时间上相互独立。然而,这不是一个实际的假设,例如,在视频应用中,$L_t$是背景图像序列,并且人们期望它随时间相关。在这项工作中,我们放松这一点,并允许$L_t$的遵循自回归模型。我们能够证明,在温和的假设下,在改变的子空间的未估计部分上的稠密假设下,具有高概率(w. h. p.),ReProCS能够始终精确地恢复$S_t$的支持集; $S_t$和$L_t$的重建误差都是时不变的小值上界;子空间恢复误差在子空间改变时间的有限延迟内衰减到小值。因为最后一个假设依赖于算法估计,所以这个结果不能被解释为正确的结果,而只是朝着正确的结果迈出了有用的一步。

英文摘要:

Online or recursive robust PCA can be posed as a problem of recovering a sparse vector, $S_t$, and a dense vector, $L_t$, which lies in a slowly changing low-dimensional subspace, from $M_t:= S_t + L_t$ on-the-fly as new data comes in. For initialization, it is assumed that an accurate knowledge of the subspace in which $L_0$ lies is available. In recent works, Qiu et al proposed and analyzed a novel solution to this problem called recursive projected compressed sensing or ReProCS. In this work, we relax one limiting assumption of Qiu et al's result. Their work required that the $L_t$'s be mutually independent over time. However this is not a practical assumption, e.g., in the video application, $L_t$ is the background image sequence and one would expect it to be correlated over time. In this work we relax this and allow the $L_t$'s to follow an autoregressive model. We are able to show that under mild assumptions and under a denseness assumption on the unestimated part of the changed subspace, with high probability (w.h.p.), ReProCS can exactly recover the support set of $S_t$ at all times; the reconstruction errors of both $S_t$ and $L_t$ are upper bounded by a time invariant and small value; and the subspace recovery error decays to a small value within a finite delay of a subspace change time. Because the last assumption depends on an algorithm estimate, this result cannot be interpreted as a correctness result but only a useful step towards it.

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。

↑