arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.05229cs.LGmath.STstat.MLstat.TH
收藏

Poisson矩阵的恢复与完备化

Poisson Matrix Recovery and Completion

Georgia Institute of Technology(佐治亚理工学院)

Yang Cao, Yao Xie

摘要:

我们扩展的低秩矩阵恢复和完成的情况下,泊松观测的线性组合或一个子集的矩阵的条目,这在各种应用中出现计数数据的理论。我们认为通常的矩阵恢复配方通过最大似然适当的限制矩阵$M$的大小$d_1$ -由- $d_2$,并建立理论上的上限和下限的恢复误差。我们的边界矩阵完成几乎是最佳的顺序$\mathcal{O}(\log(d_1 d_2))$的一个因素。这些界限是通过组合技术获得的压缩感知稀疏向量与泊松噪声和分析低秩矩阵,以及调整用于一位矩阵完成\cite{davenport20121}的参数(虽然这两个问题在性质上是不同的),适应需要新的技术,利用泊松似然函数的属性,并解决由局部子-泊松分布的高斯特性。我们的研究结果突出了一些重要的区别泊松的情况下相比,以前的工作,包括必须对每个观察到的条目和差距的上限和下限施加最小的信噪比要求。我们还开发了一组高效的迭代算法,并在合成示例和真实数据上展示了它们的良好性能。

英文摘要:

We extend the theory of low-rank matrix recovery and completion to the case when Poisson observations for a linear combination or a subset of the entries of a matrix are available, which arises in various applications with count data. We consider the usual matrix recovery formulation through maximum likelihood with proper constraints on the matrix $M$ of size $d_1$-by-$d_2$, and establish theoretical upper and lower bounds on the recovery error. Our bounds for matrix completion are nearly optimal up to a factor on the order of $\mathcal{O}(\log(d_1 d_2))$. These bounds are obtained by combing techniques for compressed sensing for sparse vectors with Poisson noise and for analyzing low-rank matrices, as well as adapting the arguments used for one-bit matrix completion \cite{davenport20121} (although these two problems are different in nature) and the adaptation requires new techniques exploiting properties of the Poisson likelihood function and tackling the difficulties posed by the locally sub-Gaussian characteristic of the Poisson distribution. Our results highlight a few important distinctions of the Poisson case compared to the prior work including having to impose a minimum signal-to-noise requirement on each observed entry and a gap in the upper and lower bounds. We also develop a set of efficient iterative algorithms and demonstrate their good performance on synthetic examples and real data.

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。

↑