Non-Bayesian Social Learning with Multiview Observations

TL;DR

This paper introduces a novel non-Bayesian social learning model that effectively integrates multiview observations from multiple viewpoints, demonstrating convergence and robustness in complex scenarios.

Contribution

It extends traditional models by incorporating multiview observations and provides theoretical convergence guarantees and robustness analysis.

Findings

Proves convergence under traditional assumptions.

Provides convergence conditions with misleading signals.

Validates robustness through numerical experiments.

Abstract

Non-Bayesian social learning enables multiple agents to conduct networked signal and information processing through observing environmental signals and information aggregating. Traditional non-Bayesian social learning models only consider single signals, limiting their applications in scenarios where multiple viewpoints of information are available. In this work, we exploit, in the information aggregation step, the independently learned results from observations taken from multiple viewpoints and propose a novel non-Bayesian social learning model for scenarios with multiview observations. We prove the convergence of the model under traditional assumptions and provide convergence conditions for the algorithm in the presence of misleading signals. Through theoretical analyses and numerical experiments, we validate the strong reliability and robustness of the proposed algorithm, showcasing its potential for real-world applications.