Knowing Who, Not How Much: Learning-Augmented Mechanisms for Consumer Utility Maximization

2026-06-30

AI Summary

This work addresses the strong impossibility of consumer utility maximization in online stochastic settings where payments conflict with allocation objectives. To overcome this limitation, the authors propose a novel learning-augmented mechanism tailored for environments with strategic agents arriving sequentially. Their approach requires only a lightweight prediction—identifying the agent with the highest value, without needing precise valuations or knowledge of the optimal solution. By integrating this minimal prediction with offline randomization techniques, they construct a deterministic truthful mechanism that achieves a constant-factor approximation to the full-information optimum when the prediction is accurate. Remarkably, even under completely erroneous predictions, the mechanism still guarantees a constant-factor approximation to the best implementable solution, thereby simultaneously ensuring consistency and robustness.

Abstract

We study consumer utility maximization in an online random-order model where strategic agents arrive sequentially. To circumvent strong impossibility results for utility maximization, we turn to the framework of learning-augmented mechanism design. Crucially, we show that the types of predictions commonly used in learning-augmented mechanism design (such as predictions of agent values or the optimal value) are not useful for utility maximization, where payments are directly at odds with the objective. Instead, we identify that a qualitatively different kind of prediction suffices: the identity of the highest-valued agent. First, we provide a deterministic truthful mechanism for our online setting by adapting offline randomized techniques. Then, we augment our mechanism with predictions. When the predictions are correct, we achieve a constant approximation to the optimal solution under full information (consistency), and even when predictions are arbitrarily bad, we guarantee a constant approximation to the best implementable solution (robustness).

Problem

• utility maximization
• learning-augmented mechanism design
• online random-order model
• strategic agents
• consumer utility

Innovation

• learning-augmented mechanism design
• consumer utility maximization
• identity prediction
• truthful mechanism
• online random-order model