Distributed estimation using reduced dimensionality sensor observations

We deal with linear estimation of random signals based on reduced-dimensionality observations collected at distributed sensors and communicated to a fusion center through wireless links. Dimensionality reduction compresses sensor data to meet low-power and bandwidth constraints, while linearity in compression and estimation are well motivated by the limited computing capabilities wireless sensor networks are envisioned to operate with. We cast this intertwined compression-estimation problem in a canonical correlation analysis framework, and derive closed-form along with coordinate descent estimators which guarantee convergence at least to a stationary point. Performance analysis and corroborating simulations demonstrate the merits of the novel distributed estimators relative to existing alternatives.