arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.07451cs.ITmath.ITstat.AP
收藏

从叠加的非线性测量恢复结构化数据

Recovering Structured Data From Superimposed Non-Linear Measurements

Martin Genzel, Peter Jung

摘要:

本文研究了非线性通信约束下的分布式数据采集问题。更具体地说,我们考虑一个模型设置$M$分布式节点采取一个未知的结构化源向量$x_0 \in \mathbb{R}^n$的单独测量,同时将其读数传送到一个中央接收器。由于该过程涉及冲突并且通常是不完美的,所以接收器测量非线性失真信号的叠加。在第一步中,我们将表明,$s$稀疏向量$x_0$可以成功地恢复从$O(s \cdot\log(2n/s))$这样的叠加测量,使用传统的Lasso估计,不依赖于任何知识的非线性腐败。然而,这种直接方法不能用于几种“未校准”的系统配置。使用$\ell^{1,2}$ -Group-Lasso可以轻松处理这些盲重建任务,但同时会增加$O(s\cdot \max\{M, \log(2n/s) \})$观测的采样率-实际上,这种提升策略的目的是将某类双线性逆问题扩展到非线性采集。我们的两个算法方法是一个更抽象的框架,其中包括亚高斯测量设计以及一般(凸)结构约束的一个特殊实例。这些结果对于各种恢复和学习任务具有独立的意义,因为它们适用于任意非线性观测模型。最后,为了说明我们的理论研究结果的实际范围,无线传感器网络的应用进行了讨论,这实际上是我们的方法的原型例子。

英文摘要:

This work deals with the problem of distributed data acquisition under non-linear communication constraints. More specifically, we consider a model setup where $M$ distributed nodes take individual measurements of an unknown structured source vector $x_0 \in \mathbb{R}^n$, communicating their readings simultaneously to a central receiver. Since this procedure involves collisions and is usually imperfect, the receiver measures a superposition of non-linearly distorted signals. In a first step, we will show that an $s$-sparse vector $x_0$ can be successfully recovered from $O(s \cdot\log(2n/s))$ of such superimposed measurements, using a traditional Lasso estimator that does not rely on any knowledge about the non-linear corruptions. This direct method however fails to work for several "uncalibrated" system configurations. These blind reconstruction tasks can be easily handled with the $\ell^{1,2}$-Group-Lasso, but coming along with an increased sampling rate of $O(s\cdot \max\{M, \log(2n/s) \})$ observations - in fact, the purpose of this lifting strategy is to extend a certain class of bilinear inverse problems to non-linear acquisition. Our two algorithmic approaches are a special instance of a more abstract framework which includes sub-Gaussian measurement designs as well as general (convex) structural constraints. These results are of independent interest for various recovery and learning tasks, as they apply to arbitrary non-linear observation models. Finally, to illustrate the practical scope of our theoretical findings, an application to wireless sensor networks is discussed, which actually serves as the prototypical example of our methodology.

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。

↑