契约的伪维度
The Pseudo-Dimension of Contracts
AI总结:
本研究通过伪维度分析契约类复杂度,为线性和有界契约提供最优权衡,并给出样本高效算法及下界,同时扩展到组合行动、契约菜单和在线学习场景。
摘要:
算法契约设计研究的是委托人激励代理人代表其付出努力的情景。在本工作中,我们关注代理人的类型从未知分布中抽取的设置,并形式化了一个离线学习框架,用于从样本代理人类型中学习近似最优契约。我们分析中的一个核心工具是统计学习理论中的伪维度概念。除了在建立样本复杂度上界方面的作用外,伪维度还衡量了一类契约的内在复杂度,为契约设计中简单性与最优性之间的权衡提供了新的视角。我们的主要结果为线性和有界契约提供了伪维度与表示误差(定义为委托人效用的损失)之间本质上最优的权衡。利用这些权衡,我们推导出了样本高效和时间高效的学习算法,并通过提供几乎匹配的样本复杂度下界来证明其近似最优性。相反,对于无界契约,我们证明了一个不可能性结果,表明不存在任何学习算法。最后,我们以三种重要方式扩展了我们的技术。首先,我们为组合行动模型提供了精细化的伪维度和样本复杂度保证,揭示了临界值数量与样本复杂度之间的新颖联系。其次,我们将结果扩展到契约菜单,表明其伪维度随菜单大小线性增长。第三,我们将算法适应于在线学习设置,在该设置中,我们表明多项式数量的类型样本足以学习近似最优的有界契约。结合先前的工作,这为该设置建立了专家建议与强盗反馈之间的正式分离。
英文摘要:
Algorithmic contract design studies scenarios where a principal incentivizes an agent to exert effort on her behalf. In this work, we focus on settings where the agent's type is drawn from an unknown distribution, and formalize an offline learning framework for learning near-optimal contracts from sample agent types. A central tool in our analysis is the notion of pseudo-dimension from statistical learning theory. Beyond its role in establishing upper bounds on the sample complexity, pseudo-dimension measures the intrinsic complexity of a class of contracts, offering a new perspective on the tradeoffs between simplicity and optimality in contract design. Our main results provide essentially optimal tradeoffs between pseudo-dimension and representation error (defined as the loss in principal's utility) with respect to linear and bounded contracts. Using these tradeoffs, we derive sample- and time-efficient learning algorithms, and demonstrate their near-optimality by providing almost matching lower bounds on the sample complexity. Conversely, for unbounded contracts, we prove an impossibility result showing that no learning algorithm exists. Finally, we extend our techniques in three important ways. First, we provide refined pseudo-dimension and sample complexity guarantees for the combinatorial actions model, revealing a novel connection between the number of critical values and sample complexity. Second, we extend our results to menus of contracts, showing that their pseudo-dimension scales linearly with the menu size. Third, we adapt our algorithms to the online learning setting, where we show that, a polynomial number of type samples suffice to learn near-optimal bounded contracts. Combined with prior work, this establishes a formal separation between expert advice and bandit feedback for this setting.
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。