Switching to Learn

TL;DR

This paper introduces a hybrid learning algorithm for agent networks that switches between Bayesian and non-Bayesian regimes, reducing communication costs while ensuring collective learning of an unknown state.

Contribution

It proposes an efficient switching method between Bayesian and non-Bayesian regimes, minimizing communication while maintaining the ability to learn the true state collectively.

Findings

The switching algorithm achieves accurate learning with fewer communication rounds.

Simulation results confirm the theoretical advantages of the proposed method.

Abstract

A network of agents attempt to learn some unknown state of the world drawn by nature from a finite set. Agents observe private signals conditioned on the true state, and form beliefs about the unknown state accordingly. Each agent may face an identification problem in the sense that she cannot distinguish the truth in isolation. However, by communicating with each other, agents are able to benefit from side observations to learn the truth collectively. Unlike many distributed algorithms which rely on all-time communication protocols, we propose an efficient method by switching between Bayesian and non-Bayesian regimes. In this model, agents exchange information only when their private signals are not informative enough; thence, by switching between the two regimes, agents efficiently learn the truth using only a few rounds of communications. The proposed algorithm preserves learnability while incurring a lower communication cost. We also verify our theoretical findings by simulation examples.