学习平台上的前瞻性推理
Look-Ahead Reasoning on Learning Platforms
AI总结：
本文探讨了学习平台中用户行为的前瞻性推理，分析了集体推理与自私行为的差异，并提出了协调效用权衡的新概念。
摘要：
在许多学习平台上，指导模型训练的优化标准反映了设计者的优先事项，而非受其影响的个人的优先事项。因此，用户可能会采取策略性行为以获得更有利的结果。虽然以往的研究已研究了学习平台上用户的战略行为，但重点大多集中在已部署模型的战略响应上，而未考虑其他用户的行为。相比之下，前瞻性推理考虑到用户行为是相互关联的，并且在大规模上会影响未来的预测。在此框架中，我们首先正式化了“层级k思考”这一来自行为经济学的概念，其中用户旨在通过一步 ahead 的方式超越他们的同行。我们证明，尽管收敛到均衡被加速，但均衡保持不变，为长期来看个体没有更高层次推理的益处。然后，我们专注于集体推理，其中用户通过优化其对模型的联合影响采取协调行动。通过对比集体行为与自私行为，我们刻画了协调的益处和限制；一个新的关于学习者和用户效用之间对齐的概念随之出现。前瞻性推理可以被视为算法集体行动的泛化；因此，我们提供了首次结果，阐述了在对抗算法系统时协调的效用权衡。
英文摘要：
On many learning platforms, the optimization criteria guiding model training reflect the priorities of the designer rather than those of the individuals they affect. Consequently, users may act strategically to obtain more favorable outcomes. While past work has studied strategic user behavior on learning platforms, the focus has largely been on strategic responses to a deployed model, without considering the behavior of other users. In contrast, look-ahead reasoning takes into account that user actions are coupled, and -- at scale -- impact future predictions. Within this framework, we first formalize level-k thinking, a concept from behavioral economics, where users aim to outsmart their peers by looking one step ahead. We show that, while convergence to an equilibrium is accelerated, the equilibrium remains the same, providing no benefit of higher-level reasoning for individuals in the long run. Then, we focus on collective reasoning, where users take coordinated actions by optimizing through their joint impact on the model. By contrasting collective with selfish behavior, we characterize the benefits and limits of coordination; a new notion of alignment between the learner's and the users' utilities emerges as a key concept. Look-ahead reasoning can be seen as a generalization of algorithmic collective action; we thus offer the first results characterizing the utility trade-offs of coordination when contesting algorithmic systems.
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。
