arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.03310stat.MEcs.ITmath.IT
收藏

最大熵低秩矩阵恢复

Maximum entropy low-rank matrix recovery

Simon Mak, Yao Xie

摘要:

在本文中,我们提出了一种新的,信息理论的方法,称为MaxEnt,有效的数据采集低秩矩阵恢复。该方法在图像处理和文本索引等领域有着广泛的应用。我们的设计方法的基础是所谓的最大熵原理,该原理指出使观测熵最大化的测量掩码也使未知矩阵$\mathbf{X}$上的信息增益最大化。结合$\mathbf{X}$的低秩随机模型,这样的原理(i)揭示了信息理论采样和子空间填充之间的新联系,以及(ii)产生用于矩阵恢复的有效掩模构造算法,其显著优于随机测量。我们说明了MaxEnt在模拟实验中的有效性,并证明了它的实用性在两个现实世界中的应用程序的图像恢复和文本文档索引。

英文摘要:

We propose in this paper a novel, information-theoretic method, called MaxEnt, for efficient data acquisition for low-rank matrix recovery. This proposed method has important applications to a wide range of problems, including image processing and text document indexing. Fundamental to our design approach is the so-called maximum entropy principle, which states that the measurement masks which maximize the entropy of observations, also maximize the information gain on the unknown matrix $\mathbf{X}$. Coupled with a low-rank stochastic model for $\mathbf{X}$, such a principle (i) reveals novel connections between information-theoretic sampling and subspace packings, and (ii) yields efficient mask construction algorithms for matrix recovery, which significantly outperforms random measurements. We illustrate the effectiveness of MaxEnt in simulation experiments, and demonstrate its usefulness in two real-world applications on image recovery and text document indexing.

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。

↑