arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.01720cs.ITmath.IT
收藏

具有先验子空间信息的加权矩阵完备化与恢复

Weighted Matrix Completion and Recovery with Prior Subspace Information

Armin Eftekhari, Dehui Yang, Michael B. Wakin

摘要:

一个不相干的低秩矩阵可以有效地重建后,观察它的一些元素在随机,然后解决一个凸规划,最小化核范数。在许多应用中,除了这些条目之外,关于矩阵的列和行空间的潜在有价值的先验知识也可用于从业者。在本文中,我们将这种先验知识纳入矩阵完成--通过最小化加权核范数--并精确量化任何改进。特别是,我们发现,在理论上,可靠的先验知识减少了样本的复杂性矩阵完成的对数因子,和观察到的改善数值模拟是相当多的放大。我们也提出了类似的结果,从通用线性测量矩阵恢复密切相关的问题。

英文摘要:

An incoherent low-rank matrix can be efficiently reconstructed after observing a few of its entries at random, and then solving a convex program that minimizes the nuclear norm. In many applications, in addition to these entries, potentially valuable prior knowledge about the column and row spaces of the matrix is also available to the practitioner. In this paper, we incorporate this prior knowledge in matrix completion---by minimizing a weighted nuclear norm---and precisely quantify any improvements. In particular, we find in theory that reliable prior knowledge reduces the sample complexity of matrix completion by a logarithmic factor, and the observed improvement in numerical simulations is considerably more magnified. We also present similar results for the closely related problem of matrix recovery from generic linear measurements.

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。

↑