Litcius/Paper detail

On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference

Mert Kayaalp, Yunus İnan, Emre Telatar, Ali H. Sayed

2023IEEE Transactions on Automatic Control41 citationsDOIOpen Access PDF

Abstract

We study the asymptotic learning rates of belief vectors in a distributed hypothesis testing problem under linear and log-linear combination rules. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We examine the gap between the rates in terms of network connectivity and information diversity. We also provide closed-form expressions for special cases involving federated architectures and exchangeable networks.

Topics & Concepts

InferenceFusionComputer scienceExponential growthSensor fusionTheoretical computer scienceMathematicsArtificial intelligenceAlgorithmLinguisticsPhilosophyMathematical analysisDistributed Sensor Networks and Detection AlgorithmsTarget Tracking and Data Fusion in Sensor NetworksBayesian Modeling and Causal Inference
On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference | Litcius