Skip to yearly menu bar Skip to main content


Poster

Accelerated consensus via Min-Sum Splitting

Patrick Rebeschini · Sekhar C Tatikonda

Pacific Ballroom #173

Keywords: [ Convex Optimization ] [ Belief Propagation ]


Abstract:

We apply the Min-Sum message-passing protocol to solve the consensus problem in distributed optimization. We show that while the ordinary Min-Sum algorithm does not converge, a modified version of it known as Splitting yields convergence to the problem solution. We prove that a proper choice of the tuning parameters allows Min-Sum Splitting to yield subdiffusive accelerated convergence rates, matching the rates obtained by shift-register methods. The acceleration scheme embodied by Min-Sum Splitting for the consensus problem bears similarities with lifted Markov chains techniques and with multi-step first order methods in convex optimization.

Live content is unavailable. Log in and register to view live content