arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.04898cs.GTcs.CRcs.DScs.LG
收藏

通过弱差分隐私在线学习实现纳什激励兼容在线机制学习

Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning

University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

Joon Suk Huh, Kirthevasan Kandasamy

AI总结:

本文提出一种结合弱差分隐私在线学习与承诺机制的随机选择方法,在无需智能体类型先验的情况下实现多轮激励兼容在线机制学习,并在对抗环境中获得随远视程度和机制类大小优雅扩展的遗憾界。

摘要:

我们研究一个多轮机制设计问题,其中我们在多个轮次上与一组智能体交互。我们希望设计一个激励兼容(IC)的在线学习方案,以在给定的机制类内最大化特定应用的目标,而无需事先了解智能体的类型分布。即使该类中的每个机制在单轮中是激励兼容的,如果算法在每一轮中天真地从该类中选择机制,整个学习过程对于在多轮中出现的非短视买家可能不是激励兼容的。在每一轮中,我们的方法在弱差分隐私在线学习算法(例如 Hedge)的推荐与一个惩罚非真实行为的承诺机制之间随机选择。我们的方法是激励兼容的,并在对抗性设置中针对特定应用的目标实现 $O(T^{\ rac{1+h}{2}})$ 的遗憾,其中 $h$ 量化了智能体的远视程度。与先前工作相比,我们的方法在概念上更简单,适用于一般的机制设计问题(超越拍卖),并且其遗憾随机制类的大小优雅地扩展。

英文摘要:

We study a multi-round mechanism design problem, where we interact with a set of agents over a sequence of rounds. We wish to design an incentive-compatible (IC) online learning scheme to maximize an application-specific objective within a given class of mechanisms, without prior knowledge of the agents' type distributions. Even if each mechanism in this class is IC in a single round, if an algorithm naively chooses from this class on each round, the entire learning process may not be IC against non-myopic buyers who appear over multiple rounds. On each round, our method randomly chooses between the recommendation of a weakly differentially private online learning algorithm (e.g., Hedge), and a commitment mechanism which penalizes non-truthful behavior. Our method is IC and achieves $O(T^{\frac{1+h}{2}})$ regret for the application-specific objective in an adversarial setting, where $h$ quantifies the long-sightedness of the agents. When compared to prior work, our approach is conceptually simpler,it applies to general mechanism design problems (beyond auctions), and its regret scales gracefully with the size of the mechanism class.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑