Higher Dimensional Consensus: Learning in Large-Scale Networks

TL;DR

This paper introduces higher dimensional consensus (HDC), a framework for large-scale networks that generalizes average consensus, enabling various network tasks and addressing the inverse problem of learning optimal weights through multi-objective optimization.

Contribution

It proposes a novel HDC framework that unifies multiple network tasks and develops a Pareto optimality approach for learning optimal weights in resource-constrained networks.

Findings

HDC converges to a linear combination of anchor states under certain conditions.

The Pareto front characterizes tradeoffs between convergence speed and final state quality.

The MOP approach effectively solves the inverse learning problem in HDC.

Abstract

The paper presents higher dimension consensus (HDC) for large-scale networks. HDC generalizes the well-known average-consensus algorithm. It divides the nodes of the large-scale network into anchors and sensors. Anchors are nodes whose states are fixed over the HDC iterations, whereas sensors are nodes that update their states as a linear combination of the neighboring states. Under appropriate conditions, we show that the sensor states converge to a linear combination of the anchor states. Through the concept of anchors, HDC captures in a unified framework several interesting network tasks, including distributed sensor localization, leader-follower, distributed Jacobi to solve linear systems of algebraic equations, and, of course, average-consensus. In many network applications, it is of interest to learn the weights of the distributed linear algorithm so that the sensors converge to a desired state. We term this inverse problem the HDC learning problem. We pose learning in HDC as a constrained non-convex optimization problem, which we cast in the framework of multi-objective optimization (MOP) and to which we apply Pareto optimality. We prove analytically relevant properties of the MOP solutions and of the Pareto front from which we derive the solution to learning in HDC. Finally, the paper shows how the MOP approach resolves interesting tradeoffs (speed of convergence versus quality of the final state) arising in learning in HDC in resource constrained networks.