Meta-Learning for Repeated Bayesian Persuasion

2026-03-20

AI Summary

This work addresses the underutilization of cross-task structural similarities in repeated Bayesian persuasion settings by proposing a unified algorithmic framework that integrates meta-learning with online learning to optimize signaling strategies under both full-feedback and bandit-feedback regimes. The approach provides the first theoretical guarantees for repeated persuasion tasks, achieving improved regret bounds over existing methods under a task similarity assumption while maintaining robust performance against arbitrary task sequences in single-round interactions. Theoretical analysis demonstrates a significant improvement in regret rates, and numerical experiments further corroborate the practical benefits of meta-learning in enhancing persuasion efficiency.

Technology Category

• Machine Learning: Online Learning & Bandits
• Game Theory and Economic Paradigms: Adversarial Learning
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Classical Bayesian persuasion studies how a sender influences receivers through carefully designed signaling policies within a single strategic interaction. In many real-world environments, such interactions are repeated across multiple games, creating opportunities to exploit structural similarity across tasks. In this work, we introduce Meta-Persuasion algorithms, establishing the first line of theoretical results for both full-feedback and bandit-feedback settings in the Online Bayesian Persuasion (OBP) and Markov Persuasion Process (MPP) frameworks. We show that our proposed meta-persuasion algorithms achieve provably sharper regret rates under natural notions of task similarity, improving upon the best-known convergence rates for both OBP and MPP. At the same time, they recover the standard single-game guarantees when the sequence of games is picked arbitrarily. Finally, we complement our theoretical analysis with numerical experiments that highlight our regret improvements and the benefits of meta-learning in repeated persuasion environments.

Problem

• Bayesian Persuasion
• Meta-Learning
• Repeated Games
• Online Learning
• Task Similarity

Innovation

• Meta-Learning
• Bayesian Persuasion
• Regret Minimization
• Online Learning
• Markov Persuasion Process