arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1009.2118cs.ITmath.ITmath.STstat.TH
收藏

限制强凸性与加权矩阵完备化:带噪声的最优界

Restricted strong convexity and weighted matrix completion: Optimal bounds with noise

Sahand Negahban, Martin J. Wainwright

摘要:

本文研究了一类行/列加权项式抽样下的矩阵完备化问题,并将均匀项式抽样的情形作为特例。我们分析了相应的随机观测算子,证明了它以很高的概率满足关于加权Frobenius范数的一种限制强凸性。利用这一性质,我们得到的推论矩阵完成的加权Frobenius范数噪声采样下的精确和近低秩矩阵的误差界。我们的研究结果是基于措施的“尖峰”和“低秩”的矩阵,比以前的工作中施加的不相干条件的限制性较小。我们的技术涉及$M$估计,包括控制的解决方案的秩和尖峰,我们建立非渐近误差界加权Frobenius范数恢复矩阵躺在$\ell_q$ -“球”的有界尖峰。使用信息论的方法,我们表明,没有算法可以实现更好的估计(对数因子)在这些相同的集合,表明我们的条件矩阵和相关的利率基本上是最优的。

英文摘要:

We consider the matrix completion problem under a form of row/column weighted entrywise sampling, including the case of uniform entrywise sampling as a special case. We analyze the associated random observation operator, and prove that with high probability, it satisfies a form of restricted strong convexity with respect to weighted Frobenius norm. Using this property, we obtain as corollaries a number of error bounds on matrix completion in the weighted Frobenius norm under noisy sampling and for both exact and near low-rank matrices. Our results are based on measures of the "spikiness" and "low-rankness" of matrices that are less restrictive than the incoherence conditions imposed in previous work. Our technique involves an $M$-estimator that includes controls on both the rank and spikiness of the solution, and we establish non-asymptotic error bounds in weighted Frobenius norm for recovering matrices lying with $\ell_q$-"balls" of bounded spikiness. Using information-theoretic methods, we show that no algorithm can achieve better estimates (up to a logarithmic factor) over these same sets, showing that our conditions on matrices and associated rates are essentially optimal.

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。

↑