LGAIMASISPMar 10, 2023

On the Fusion Strategies for Federated Decision Making

arXiv:2303.06109v25 citationsh-index: 87
AI Analysis

This work addresses efficient and private decision-making for distributed agents, but it appears incremental as it builds on previous work to compare fusion strategies.

The paper tackles the problem of information aggregation in federated decision making by analyzing non-Bayesian social learning strategies, where agents use Bayes rule and a central processor aggregates opinions via arithmetic or geometric averaging, establishing asymptotic normality and deriving approximate error probability expressions.

We consider the problem of information aggregation in federated decision making, where a group of agents collaborate to infer the underlying state of nature without sharing their private data with the central processor or each other. We analyze the non-Bayesian social learning strategy in which agents incorporate their individual observations into their opinions (i.e., soft-decisions) with Bayes rule, and the central processor aggregates these opinions by arithmetic or geometric averaging. Building on our previous work, we establish that both pooling strategies result in asymptotic normality characterization of the system, which, for instance, can be utilized to derive approximate expressions for the error probability. We verify the theoretical findings with simulations and compare both strategies.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes