arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.05951stat.MLcs.ITcs.LGmath.IT
收藏

从线性测量混合信号中恢复稀疏信号的支持度

Support Recovery of Sparse Signals from a Mixture of Linear Measurements

Syracuse University(雪城大学);University of California, San Diego(加州大学圣地亚哥分校);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Venkata Gandikota, Arya Mazumdar, Soumyabrata Pal

摘要:

从简单测量恢复稀疏向量的支持是一个广泛研究的问题,在压缩感知,1位压缩感知和更一般的单索引模型的框架下考虑。我们考虑这个问题的概括:混合物的线性回归,线性分类器的混合物,其中的目标是恢复支持的多个稀疏向量,只使用少量的可能有噪声的线性,1位测量分别。关键的挑战是来自不同向量的测量值是随机混合的。这两个问题最近也受到关注。在线性分类器的混合中,观测对应于随机未知向量所在的查询超平面的一侧,而在线性回归的混合中,我们观察到随机未知向量在查询超平面上的投影。从混合中恢复未知向量的主要步骤是首先识别所有单个分量向量的支持。在这项工作中,我们研究的测量数量足以恢复所有的分量向量的支持在这两个模型的混合物。我们提供的算法,使用一些测量多项式在$k, \log n$和准多项式在$\ell$,恢复支持的所有$\ell$未知向量的混合物具有高概率时,每个单独的组件是一个$k$稀疏$n$维向量。

英文摘要:

Recovery of support of a sparse vector from simple measurements is a widely-studied problem, considered under the frameworks of compressed sensing, 1-bit compressed sensing, and more general single index models. We consider generalizations of this problem: mixtures of linear regressions, and mixtures of linear classifiers, where the goal is to recover supports of multiple sparse vectors using only a small number of possibly noisy linear, and 1-bit measurements respectively. The key challenge is that the measurements from different vectors are randomly mixed. Both of these problems have also received attention recently. In mixtures of linear classifiers, the observations correspond to the side of queried hyperplane a random unknown vector lies in, whereas in mixtures of linear regressions we observe the projection of a random unknown vector on the queried hyperplane. The primary step in recovering the unknown vectors from the mixture is to first identify the support of all the individual component vectors. In this work, we study the number of measurements sufficient for recovering the supports of all the component vectors in a mixture in both these models. We provide algorithms that use a number of measurements polynomial in $k, \log n$ and quasi-polynomial in $\ell$, to recover the support of all the $\ell$ unknown vectors in the mixture with high probability when each individual component is a $k$-sparse $n$-dimensional vector.

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。

↑