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 1912.07152eess.SYcs.SYmath.OC
收藏

基于矩阵分解的具有潜在节点的线性动力系统的拓扑学习

Topology Learning of Linear Dynamical Systems with Latent Nodes using Matrix Decomposition

Mishfad S. V., Harish Doddi, Murti V. Salapaka

摘要:

本文提出了一种新的方法来重构具有潜在节点的网络化线性动力系统的拓扑结构。网络允许有向环和双向边。主要方法依赖于从观测节点获得的功率谱密度矩阵(IPSDM)的逆作为稀疏和低秩矩阵之和的唯一分解。我们提供的条件和方法分解成稀疏和低秩组件的观察节点的IPSDM。稀疏组件产生与观察到的节点相关联的道德图,并且低秩组件检索隐藏节点的父母、孩子和配偶(马尔可夫毯)。给出了一个给定的反对称矩阵唯一分解为一个稀疏反对称矩阵与一个低秩反对称矩阵之和的充要条件。它示出,对于一个大的类的系统,观察到的节点的IPSDM的虚部的唯一分解,斜对称矩阵,到稀疏和低秩组件是足够的,以确定观察到的节点的道德图以及潜在的节点的马尔可夫毯。对于一个大类的系统,所有虚假的链接所形成的观察节点的道德图可以识别。假设可识别性所需的隐藏节点上的条件,隐藏节点和观察到的节点之间的链接可以被重建,从而从IPSDM的可用性中检索网络的确切拓扑。此外,对于有限数量的数据样本,我们提供了浓度边界上的条目之间的距离真正的IPSDM和估计IPSDM。

英文摘要:

In this article, we present a novel approach to reconstruct the topology of networked linear dynamical systems with latent nodes. The network is allowed to have directed loops and bi-directed edges. The main approach relies on the unique decomposition of the inverse of power spectral density matrix (IPSDM) obtained from observed nodes as a sum of sparse and low-rank matrices. We provide conditions and methods for decomposing the IPSDM of the observed nodes into sparse and low-rank components. The sparse component yields the moral graph associated with the observed nodes, and the low-rank component retrieves parents, children and spouses (the Markov Blanket) of the hidden nodes. The article provides necessary and sufficient conditions for the unique decomposition of a given skew symmetric matrix into sum of a sparse skew symmetric and a low-rank skew symmetric matrices. It is shown that for a large class of systems, the unique decomposition of imaginary part of the IPSDM of observed nodes, a skew symmetric matrix, into the sparse and the low-rank components is sufficient to identify the moral graph of the observed nodes as well as the Markov Blanket of latent nodes. For a large class of systems, all spurious links in the moral graph formed by the observed nodes can be identified. Assuming conditions on hidden nodes required for identifiability, links between the hidden and observed nodes can be reconstructed, resulting in the retrieval of the exact topology of the network from the availability of IPSDM. Moreover, for finite number of data samples, we provide concentration bounds on the entry-wise distance between the true IPSDM and the estimated IPSDM.

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。

↑