arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1506.07615cs.ITcs.LGcs.NAmath.ITmath.NAstat.ML
收藏

一般基中用少系数的败坏样本完备低秩矩阵

Completing Low-Rank Matrices with Corrupted Samples from Few Coefficients in General Basis

Carnegie Mellon University(卡内基梅隆大学);Peking University(北京大学);Shanghai Jiao Tong University(上海交通大学)

Hongyang Zhang, Zhouchen Lin, Chao Zhang

摘要:

从损坏和丢失的数据中恢复子空间对于信号处理和信息论中的各种应用是至关重要的。为了完成缺失值和检测列损坏,现有的鲁棒矩阵完成(MC)方法大多集中于从少量损坏系数w.r.t.标准基础,但不适用于更一般的基础,例如,傅立叶基本文证明了秩为$r$的$m\times n$矩阵的值域空间可以由较少的系数w. r. t精确地恢复。一般的基础上,虽然$r$和损坏的样本的数量都高达$O(\min\{m,n\}/\log^3 (m+n))$。我们的模型涵盖了以前的特殊情况下,和强大的MC可以恢复具有更高的秩的内在矩阵。此外,我们建议一个通用的正则化参数,这是$λ=1/\sqrt{\log n}$的选择。通过我们的$\ell_{2,1}$滤波算法,这是有理论保证的,我们可以进一步减少我们的模型的计算成本。作为应用,我们还发现扩展的鲁棒低秩表示和扩展的鲁棒MC的解是相互可表达的,因此在一定条件下,我们的理论和算法都可以应用于具有缺失值的子空间聚类问题.实验验证了我们的理论。

英文摘要:

Subspace recovery from corrupted and missing data is crucial for various applications in signal processing and information theory. To complete missing values and detect column corruptions, existing robust Matrix Completion (MC) methods mostly concentrate on recovering a low-rank matrix from few corrupted coefficients w.r.t. standard basis, which, however, does not apply to more general basis, e.g., Fourier basis. In this paper, we prove that the range space of an $m\times n$ matrix with rank $r$ can be exactly recovered from few coefficients w.r.t. general basis, though $r$ and the number of corrupted samples are both as high as $O(\min\{m,n\}/\log^3 (m+n))$. Our model covers previous ones as special cases, and robust MC can recover the intrinsic matrix with a higher rank. Moreover, we suggest a universal choice of the regularization parameter, which is $λ=1/\sqrt{\log n}$. By our $\ell_{2,1}$ filtering algorithm, which has theoretical guarantees, we can further reduce the computational cost of our model. As an application, we also find that the solutions to extended robust Low-Rank Representation and to our extended robust MC are mutually expressible, so both our theory and algorithm can be applied to the subspace clustering problem with missing values under certain conditions. Experiments verify our theories.

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。

↑