arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1009.0861stat.MLcs.AIcs.LG
收藏

关于相干性的估计

On the Estimation of Coherence

Courant Institute(柯朗研究所);Google Research(谷歌研究院);University of California, Berkeley(加州大学伯克利分校)

Mehryar Mohri, Ameet Talwalkar

摘要:

低秩矩阵近似通常用于帮助将标准机器学习算法扩展到大规模问题。最近,矩阵相干性已经被用于表征在这些低秩近似和其他基于采样的算法的上下文中从矩阵条目的子集提取全局信息的能力,例如,矩阵完备,鲁棒PCA。由于相干性是根据矩阵的奇异向量定义的,计算起来很昂贵,这些结果的实际意义在很大程度上取决于以下问题:我们能否有效地和准确地估计矩阵的相干性?在本文中,我们解决这个问题。我们提出了一种新的算法,从少量的列估计的一致性,正式分析其行为,并推导出一个新的基于一致性的矩阵近似界的基础上,这种分析。然后,我们提出了广泛的合成和真实数据集的实验结果,证实了我们的最坏情况下的理论分析,但提供强有力的支持,使用我们提出的算法时,低秩近似被认为是。我们的算法有效地,准确地估计矩阵的一致性在广泛的数据集,这些一致性估计是基于抽样的矩阵近似的有效性在个案的基础上很好的预测。

英文摘要:

Low-rank matrix approximations are often used to help scale standard machine learning algorithms to large-scale problems. Recently, matrix coherence has been used to characterize the ability to extract global information from a subset of matrix entries in the context of these low-rank approximations and other sampling-based algorithms, e.g., matrix com- pletion, robust PCA. Since coherence is defined in terms of the singular vectors of a matrix and is expensive to compute, the practical significance of these results largely hinges on the following question: Can we efficiently and accurately estimate the coherence of a matrix? In this paper we address this question. We propose a novel algorithm for estimating coherence from a small number of columns, formally analyze its behavior, and derive a new coherence-based matrix approximation bound based on this analysis. We then present extensive experimental results on synthetic and real datasets that corroborate our worst-case theoretical analysis, yet provide strong support for the use of our proposed algorithm whenever low-rank approximation is being considered. Our algorithm efficiently and accurately estimates matrix coherence across a wide range of datasets, and these coherence estimates are excellent predictors of the effectiveness of sampling-based matrix approximation on a case-by-case basis.

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。

↑