arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.06327stat.MLcs.DScs.LGcs.NAmath.NA
收藏

从少量条目中估计谱

Spectrum Estimation from a Few Entries

University of Illinois Urbana Champaign(伊利诺伊大学厄巴纳-香槟分校)

Ashish Khetan, Sewoong Oh

AI总结:

本文研究从矩阵部分条目中恢复谱性质的问题,提出通过估计Schatten范数和Chebyshev逼近或Wasserstein距离匹配来高效恢复奇异值,理论分析显示其比低秩矩阵恢复需要更少样本。

摘要:

矩阵数据的奇异值提供了数据结构、有效维数和高阶数据分析工具超参数选择的见解。然而,在协同过滤和网络分析等实际应用中,我们只能获取部分观测。本文考虑从矩阵条目采样中恢复底层矩阵谱性质的基本问题。我们特别关注直接恢复奇异值集合以及样本高效恢复谱总和函数的方法。首先估计矩阵的Schatten k-范数,然后应用Chebyshev逼近谱总和函数或在Wasserstein距离中进行矩匹配以恢复奇异值。主要技术挑战是准确估计Schatten范数。我们引入基于图中小结构计数的无偏估计器,并提供与实测性能相匹配的保证。理论分析表明,Schatten范数可以从比恢复低秩矩阵所需更少的样本中准确恢复。数值实验表明,我们显著优于使用矩阵补全方法的竞争对手方法。

英文摘要:

Singular values of a data in a matrix form provide insights on the structure of the data, the effective dimensionality, and the choice of hyper-parameters on higher-level data analysis tools. However, in many practical applications such as collaborative filtering and network analysis, we only get a partial observation. Under such scenarios, we consider the fundamental problem of recovering spectral properties of the underlying matrix from a sampling of its entries. We are particularly interested in directly recovering the spectrum, which is the set of singular values, and also in sample-efficient approaches for recovering a spectral sum function, which is an aggregate sum of the same function applied to each of the singular values. We propose first estimating the Schatten $k$-norms of a matrix, and then applying Chebyshev approximation to the spectral sum function or applying moment matching in Wasserstein distance to recover the singular values. The main technical challenge is in accurately estimating the Schatten norms from a sampling of a matrix. We introduce a novel unbiased estimator based on counting small structures in a graph and provide guarantees that match its empirical performance. Our theoretical analysis shows that Schatten norms can be recovered accurately from strictly smaller number of samples compared to what is needed to recover the underlying low-rank matrix. Numerical experiments suggest that we significantly improve upon a competing approach of using matrix completion methods.

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。

↑