arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.05885cs.LGstat.ML
收藏

带噪声的杠杆化矩阵补全

Leveraged Matrix Completion with Noise

Nanjing University of Science and Technology(南京理工大学);Wuhan University(武汉大学);University of Sydney(悉尼大学)

Xinjian Huang, Weiwei Liu, Bo Du, Dacheng Tao

AI总结:

本文提出利用杠杆分数刻画元素重要性并设计非均匀采样过程,在放宽非相干性和均匀观测假设的条件下,仅需约 $\mathcal{O}(nr\log^2 n)$ 个含噪条目即可可证明地恢复低秩矩阵。

摘要:

从子采样测量中补全低秩矩阵在过去十年中受到了广泛关注。现有工作表明,在一些相当严格的假设下,需要 $\mathcal{O}(nr\log^2(n))$ 个数据点才能在理论上以高概率保证完成对一个 $n \times n$、秩为 $r$ 的含噪矩阵的补全,这些假设包括:(1) 底层矩阵必须是非相干的;(2) 观测服从均匀分布。这种限制性部分源于忽略了杠杆分数以及每个元素的先验信息的作用。在本文中,我们利用杠杆分数来刻画每个元素的重要性,并将假设显著放宽为:(1) 不对底层低秩矩阵施加任何其他结构假设;(2) 被观测的元素通过杠杆分数适当地依赖于其重要性。在这些假设下,我们设计了一种非均匀/有偏采样过程,以替代均匀采样,从而能够揭示每个被观测元素的“重要性”。我们的证明得到一种新方法的支持,该方法基于 Golfing Scheme 表述充分最优性条件,这对更广泛的领域也具有独立的研究意义。理论结果表明,我们能够仅从大约 $\mathcal{O}(nr\log^2 (n))$ 个条目中可证明地恢复一个未知的 $n\times n$、秩为 $r$ 的矩阵,即使被观测的条目受到少量噪声信息的污染。实证结果与我们的理论完全一致。

英文摘要:

Completing low-rank matrices from subsampled measurements has received much attention in the past decade. Existing works indicate that $\mathcal{O}(nr\log^2(n))$ datums are required to theoretically secure the completion of an $n \times n$ noisy matrix of rank $r$ with high probability, under some quite restrictive assumptions: (1) the underlying matrix must be incoherent; (2) observations follow the uniform distribution. The restrictiveness is partially due to ignoring the roles of the leverage score and the oracle information of each element. In this paper, we employ the leverage scores to characterize the importance of each element and significantly relax assumptions to: (1) not any other structure assumptions are imposed on the underlying low-rank matrix; (2) elements being observed are appropriately dependent on their importance via the leverage score. Under these assumptions, instead of uniform sampling, we devise an ununiform/biased sampling procedure that can reveal the ``importance'' of each observed element. Our proofs are supported by a novel approach that phrases sufficient optimality conditions based on the Golfing Scheme, which would be of independent interest to the wider areas. Theoretical findings show that we can provably recover an unknown $n\times n$ matrix of rank $r$ from just about $\mathcal{O}(nr\log^2 (n))$ entries, even when the observed entries are corrupted with a small amount of noisy information. The empirical results align precisely with our theories.

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。

↑