arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0901.3150cs.LGstat.ML
收藏

由几个子元素完成矩阵

Matrix Completion from a Few Entries

Stanford University(斯坦福大学)

Raghunandan H. Keshavan, Andrea Montanari, Sewoong Oh

摘要:

设M是秩r<<n的随机(α n)× n矩阵,并假设其元素的一致随机子集E被观测到。我们描述了一个有效的算法,重建M从|E| = O(rn)观察到的项目与相对均方根误差RMSE <= C(rn/ |E|)^0.5。此外,如果r=O(1),则可以从|E| = O(n log(n))个条目精确地重构M。这些结果不仅适用于随机矩阵,也适用于一般的低秩非相干矩阵。这解决了(在有界秩的情况下)Candes和Recht留下的一个问题,并改善了他们的重建算法的保证。算法的复杂度为O(|E| r log(n)),这为算法在大规模数据集上的应用开辟了道路。在证明这些结论的过程中,我们推广了Friedman-Kahn-Szemeredi和Feige-Ofek关于稀疏随机矩阵谱的一个著名结果。

英文摘要:

Let M be a random (alpha n) x n matrix of rank r<<n, and assume that a uniformly random subset E of its entries is observed. We describe an efficient algorithm that reconstructs M from |E| = O(rn) observed entries with relative root mean square error RMSE <= C(rn/|E|)^0.5 . Further, if r=O(1), M can be reconstructed exactly from |E| = O(n log(n)) entries. These results apply beyond random matrices to general low-rank incoherent matrices. This settles (in the case of bounded rank) a question left open by Candes and Recht and improves over the guarantees for their reconstruction algorithm. The complexity of our algorithm is O(|E|r log(n)), which opens the way to its use for massive data sets. In the process of proving these statements, we obtain a generalization of a celebrated result by Friedman-Kahn-Szemeredi and Feige-Ofek on the spectrum of sparse random matrices.

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。

↑