Distributed Detection over Adaptive Networks: Refined Asymptotics and the Role of Connectivity

TL;DR

This paper refines the asymptotic analysis of distributed detection over adaptive networks, revealing how network connectivity influences error probabilities and emphasizing the importance of connectivity in performance.

Contribution

It extends previous large deviations results by applying exact asymptotics, providing a detailed understanding of how network connectivity affects detection error probabilities.

Findings

Error probabilities decay exponentially with 1/μ

More connected agents achieve lower error probabilities

Network topology significantly influences detection performance

Abstract

We consider distributed detection problems over adaptive networks, where dispersed agents learn continually from streaming data by means of local interactions. The simultaneous requirements of adaptation and cooperation are achieved by employing diffusion algorithms with constant step-size {\mu}. In [1], [2] some main features of adaptive distributed detection were revealed. By resorting to large deviations analysis, it was established that the Type-I and Type-II error probabilities of all agents vanish exponentially as functions of 1/{\mu}, and that all agents share the same Type-I and Type-II error exponents. However, numerical evidences presented in [1], [2] showed that the theory of large deviations does not capture the fundamental impact of network connectivity on performance, and that additional tools and efforts are required to obtain accurate predictions for the error probabilities. This work addresses these open issues and extends the results of [1], [2] in several directions. By conducting a refined asymptotic analysis based on the mathematical framework of exact asymptotics, we arrive at a revealing and powerful understanding of the universal behavior of distributed detection over adaptive networks: as functions of 1/{\mu}, the error (log-)probability curves corresponding to different agents stay nearly-parallel to each other (as already discovered in [1], [2]), however, these curves are ordered following a criterion reflecting the degree of connectivity of each agent. Depending on the combination weights, the more connected an agent is, the lower its error probability curve will be. Interesting and somehow unexpected behaviors emerge, in terms of the interplay between the network topology, the combination weights, and the inference performance. The lesson learned is that connectivity matters.