arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.06302stat.MEstat.ML
收藏

关于从少量数据恢复最佳秩-r逼近

On Recovering the Best Rank-r Approximation from Few Entries

Shun Xu, Ming Yuan

摘要:

在这篇笔记中,我们研究如何以及我们可以重建的最佳秩$r$近似的一个大矩阵,从它的少数项目。我们表明,即使一个数据矩阵是满秩的,不能很好地近似低秩矩阵,它的最佳低秩近似仍然可以可靠地计算或估计从少量的条目。从统计学的角度来看,这是特别相关的:数据矩阵的最佳低秩近似往往比其本身更令人感兴趣,因为它们捕获了更稳定的特性,并且通常具有更可重现的特性,否则会产生复杂的数据生成模型。特别是,我们调查两个不可知的方法:第一个是基于谱截断;第二个是基于投影梯度下降的优化过程。我们认为,虽然第一种方法是直观和合理有效的,后者具有更优越的性能一般。我们表明,误差取决于如何接近矩阵是低秩。理论和数值证据证明所提出的方法的有效性。

英文摘要:

In this note, we investigate how well we can reconstruct the best rank-$r$ approximation of a large matrix from a small number of its entries. We show that even if a data matrix is of full rank and cannot be approximated well by a low-rank matrix, its best low-rank approximations may still be reliably computed or estimated from a small number of its entries. This is especially relevant from a statistical viewpoint: the best low-rank approximations to a data matrix are often of more interest than itself because they capture the more stable and oftentimes more reproducible properties of an otherwise complicated data-generating model. In particular, we investigate two agnostic approaches: the first is based on spectral truncation; and the second is a projected gradient descent based optimization procedure. We argue that, while the first approach is intuitive and reasonably effective, the latter has far superior performance in general. We show that the error depends on how close the matrix is to being of low rank. Both theoretical and numerical evidence is presented to demonstrate the effectiveness of the proposed approaches.

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。

↑