Learning to Persuade Privately Informed Receivers

2026-07-30

AI Summary

This work addresses Bayesian persuasion in settings where the receiver possesses private information unobservable to the sender, rendering classical models inapplicable. The paper studies an online Bayesian persuasion problem in which the sender must learn an optimal information-disclosure policy solely by observing the receiver’s actions. The key innovation lies in transforming the exponentially complex belief-space learning problem into a one-dimensional change-point detection task, substantially reducing computational complexity. By integrating techniques from online learning and change-point detection, the proposed algorithm achieves polynomial dependence on the sizes of the state space and signal alphabet, and attains a regret bound of $\widetilde{O}(T^{3/4})$ relative to the optimal policy under known private signals.

Abstract

Bayesian persuasion studies how an informed sender can influence the behavior of a receiver through strategic information disclosure. Standard models assume the sender is the receiver's only source of information, yet in many applications receivers also consult external sources the sender can neither observe nor control. We study an online Bayesian persuasion problem in which a binary-action receiver has access to a fixed signaling scheme that is unknown to the sender. Over $T$ rounds, the sender commits to a signaling scheme and sends a signal; the receiver combines it with its private signal and acts, while the sender observes only the action. We design a learning algorithm that achieves regret $\widetilde{O}(T^{3/4})$ relative to the optimal scheme of a sender who knows the private signaling scheme of the receiver, with polynomial dependence on the sizes of the state space and the receiver's signal alphabet. Our key insight is reducing the problem of learning the exponentially large belief-space partitioning induced by the private scheme to a one-dimensional change-point detection problem.

Problem

• Bayesian persuasion
• private information
• online learning
• signaling scheme
• strategic communication

Innovation

• Bayesian persuasion
• online learning
• private signaling
• change-point detection
• regret minimization