arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.06379cs.ITcs.LGmath.ITstat.ML
收藏

低秩矩阵完备化的松弛杠杆抽样

Relaxed Leverage Sampling for Low-rank Matrix Completion

Xerox Research Center India(施乐印度研究中心)

Abhisek Kundu

摘要:

我们考虑的问题,通过标准的核范数最小化框架的任何$m\times n$矩阵的秩$\varrho$从少量的观察到的条目的精确恢复。这种低秩矩阵具有自由度$(m+n)\varrho - \varrho^2$。我们发现,任何任意低秩矩阵可以完全恢复从一个$Θ\left(((m+n)\varrho - \varrho^2)\log^2(m+n)\right)$随机采样的条目,从而匹配所需的条目数的下限(在自由度方面),与一个额外的因素$O(\log^2(m+n))$。为了达到样本大小的这个界限,我们观察每个条目的概率与相应的行和列杠杆分数之和成比例,减去它们的乘积。我们表明,这种放宽抽样概率(与Chen et al,2014中的杠杆分数之和相反)可以为我们提供$O(\varrho^2\log^2(m+n))$附加改进Chen et al,2014获得的(最知名的)样本量,用于核范数最小化。实际数据的实验证实了理论上的样本容量的改善。此外,$(a)$非相干矩阵(具有受限的杠杆分数)和仅具有一个行或列空间的$(b)$矩阵的精确恢复可以使用我们的放松杠杆分数采样,经由核范数最小化,而无需先验地知道杠杆分数。在这种情况下,我们也可以提高样本量。

英文摘要:

We consider the problem of exact recovery of any $m\times n$ matrix of rank $\varrho$ from a small number of observed entries via the standard nuclear norm minimization framework. Such low-rank matrices have degrees of freedom $(m+n)\varrho - \varrho^2$. We show that any arbitrary low-rank matrices can be recovered exactly from a $Θ\left(((m+n)\varrho - \varrho^2)\log^2(m+n)\right)$ randomly sampled entries, thus matching the lower bound on the required number of entries (in terms of degrees of freedom), with an additional factor of $O(\log^2(m+n))$. To achieve this bound on sample size we observe each entry with probabilities proportional to the sum of corresponding row and column leverage scores, minus their product. We show that this relaxation in sampling probabilities (as opposed to sum of leverage scores in Chen et al, 2014) can give us an $O(\varrho^2\log^2(m+n))$ additive improvement on the (best known) sample size obtained by Chen et al, 2014, for the nuclear norm minimization. Experiments on real data corroborate the theoretical improvement on sample size. Further, exact recovery of $(a)$ incoherent matrices (with restricted leverage scores), and $(b)$ matrices with only one of the row or column spaces to be incoherent, can be performed using our relaxed leverage score sampling, via nuclear norm minimization, without knowing the leverage scores a priori. In such settings also we can achieve improvement on sample size.

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。

↑