Learning to Price with Persuasion

2026-08-17

AI Summary

This study addresses the revenue maximization challenge under information asymmetry where sellers lack knowledge of buyer beliefs. Integrating information design with mechanism design theory, we propose learning optimal signaling and pricing strategies in both batch and online query settings. Notably, this work presents the first Fully Polynomial-Time Approximation Scheme (FPTAS), resolving an open problem posed by Bergemann et al. and enabling revenue maximization computation with arbitrarily small additive loss. Furthermore, we establish sample complexity bounds for both settings, offering novel learning-theoretic perspectives and efficient computational frameworks for economic scenarios characterized by asymmetric information.

Abstract

Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mechanism design. Specifically, we consider the economic setting recently introduced by Bergemann et al. (2022), where in addition to the menu of quality-price pairs, the seller offers information on the value of the match between product quality and buyer's taste via a signaling scheme. We relax the assumption that the seller knows the buyers' belief about the distribution of tastes and study the sample requirements of designing a revenue maximizing scheme. We consider both the batch setting where we have access to data from a set of i.i.d. buyers and an online demand query model where we observe the buyers' behaviors to seller's schemes. Despite the apparent non-convexity of the problem, we also give the first FPTAS to compute a scheme that maximizes the revenue within an arbitrarily small additive loss, which was left open by Bergemann et al. (2022). Overall, this brings a new learning perspective in asymmetric economic settings where buyers and sellers know different types of information.

Problem

• Learning to Price
• Information Design
• Mechanism Design
• Sample Complexity
• Revenue Maximization

Innovation

• Information Design
• Mechanism Design
• FPTAS
• Sample Complexity
• Asymmetric Information