Friday, 19 April, 2013
SPEAKER: Prof. Ioannis Schizas - Univ. of TX - Arlington
HOST: Prof. V. Maroulas
TITLE: Distributed Determination of Informative Network Nodes via Sparsity-Cognizant Covariance Decomposition
ABSTRACT: Covariance matrices that consist of sparse factors arise in settings where the field sensed by a sensor network is formed by localized sources. In this presentation, it is shown that the task of identifying source-informative sensors boils down to estimating the support of the sparse covariance factors. Further, a novel distributed sparsity-aware matrix decomposition framework is derived to recover the support of the sparse factors of a matrix. The proposed framework relies on norm-one regularization and the notion of missing covariance entries. The associated minimization problems are solved using computationally efficient coordinate descent iterations combined with matrix deflation mechanisms. A simple scheme is also developed to set appropriately the sparsity-adjusting coefficients. The distributed framework can provably recover the support of the covariance factors when field sources do not overlap, while each subset of sensors sensing a specific source forms a connected communication graph.
Refreshments available at 3:15 p.m.