Sequential Cooperative Bayesian Inference

TL;DR

This paper provides theoretical foundations for cooperative Bayesian inference through sequential data, demonstrating its consistency, efficiency, and robustness in both human and machine learning contexts.

Contribution

It introduces novel theoretical analysis of Sequential Cooperative Bayesian Inference, establishing its general feasibility and stability.

Findings

Cooperation enhances inference consistency and convergence.

Sequential cooperative inference is sample-efficient and robust.

Theoretical results support broader applications in human and machine cooperation.

Abstract

Cooperation is often implicitly assumed when learning from other agents. Cooperation implies that the agent selecting the data, and the agent learning from the data, have the same goal, that the learner infer the intended hypothesis. Recent models in human and machine learning have demonstrated the possibility of cooperation. We seek foundational theoretical results for cooperative inference by Bayesian agents through sequential data. We develop novel approaches analyzing consistency, rate of convergence and stability of Sequential Cooperative Bayesian Inference (SCBI). Our analysis of the effectiveness, sample efficiency and robustness show that cooperation is not only possible in specific instances but theoretically well-founded in general. We discuss implications for human-human and human-machine cooperation.