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 1306.2979stat.MLcs.ITcs.LGmath.IT
收藏

可证明地完成任何低秩矩阵

Completing Any Low-rank Matrix, Provably

University of California, Berkeley(加州大学伯克利分校);The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward

摘要:

矩阵完备化,即,从其元素的一个小子集中精确且可证明地恢复低秩矩阵,目前已知仅当矩阵在其行和列空间上满足限制性结构约束--称为{ \em不相干性}时才是可能的。在这些情况下,元素的子集被随机均匀地采样。在本文中,我们表明,{ \em任何}秩- $ r $ $ n$ -由- $ n $矩阵可以完全恢复从尽可能少的$O(nr \log^2 n)$随机选择的元素,提供这种随机选择是根据一个{ \em特定的偏置分布}:任何元素被采样的概率应该是成比例的相应行和列的杠杆分数的总和。也许同样重要的是,我们表明,这种特定形式的抽样几乎是必要的,在一个自然的精确意义上,这意味着其他可能更直观的抽样方案失败。我们进一步建立了三种方法,在杠杆分数未知时将上述结果用于设置\textit{a priori}:(a)用于只有一个行或列空间不相干的情况的采样策略,(b)用于一般矩阵的双重抽样过程,首先采样以估计杠杆分数,然后采样以精确恢复,以及(c)分析显示了在非均匀采样的情况下加权核/迹范数最小化相对于香草未加权公式化的优点。

英文摘要:

Matrix completion, i.e., the exact and provable recovery of a low-rank matrix from a small subset of its elements, is currently only known to be possible if the matrix satisfies a restrictive structural constraint---known as {\em incoherence}---on its row and column spaces. In these cases, the subset of elements is sampled uniformly at random. In this paper, we show that {\em any} rank-$ r $ $ n$-by-$ n $ matrix can be exactly recovered from as few as $O(nr \log^2 n)$ randomly chosen elements, provided this random choice is made according to a {\em specific biased distribution}: the probability of any element being sampled should be proportional to the sum of the leverage scores of the corresponding row, and column. Perhaps equally important, we show that this specific form of sampling is nearly necessary, in a natural precise sense; this implies that other perhaps more intuitive sampling schemes fail. We further establish three ways to use the above result for the setting when leverage scores are not known \textit{a priori}: (a) a sampling strategy for the case when only one of the row or column spaces are incoherent, (b) a two-phase sampling procedure for general matrices that first samples to estimate leverage scores followed by sampling for exact recovery, and (c) an analysis showing the advantages of weighted nuclear/trace-norm minimization over the vanilla un-weighted formulation for the case of non-uniform sampling.

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。

↑