Distributed Resource Allocation with Binary Decisions via Newton-like Neural Network Dynamics

TL;DR

This paper introduces a Newton-like neural network method for distributed binary resource allocation, improving convergence speed and solution quality compared to traditional approaches, with theoretical guarantees and practical efficiency.

Contribution

It proposes a novel Newton-like modification to Hopfield Neural Network dynamics for distributed binary optimization, with convergence guarantees and an annealing technique for feasible solutions.

Findings

Zero probability of saddle point convergence under light assumptions

Significant runtime improvement over SDP relaxation methods

Competitive solution quality with centralized greedy approaches

Abstract

This paper aims to solve a distributed resource allocation problem with binary local constraints. The problem is formulated as a binary program with a cost function defined by the summation of agent costs plus a global mismatch/penalty term. We propose a modification of the Hopfield Neural Network (HNN) dynamics in order to solve this problem while incorporating a novel Newton-like weighting factor. This addition lends itself to fast avoidance of saddle points, which the gradient-like HNN is susceptible to. Turning to a multi-agent setting, we reformulate the problem and develop a distributed implementation of the Newton-like dynamics. We show that if a local solution to the distributed reformulation is obtained, it is also a local solution to the centralized problem. A main contribution of this work is to show that the probability of converging to a saddle point of an appropriately defined energy function in both the centralized and distributed settings is zero under light assumptions. Finally, we enlarge our algorithm with an annealing technique which gradually learns a feasible binary solution. Simulation results demonstrate that the proposed methods are competitive with centralized greedy and SDP relaxation approaches in terms of solution quality, while the main advantage of our approach is a significant improvement in runtime over the SDP relaxation method and the distributed quality of implementation.