论文标题
游戏有帮助！从自然动态中的战略互动中学习
Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
论文作者
论文摘要
我们考虑一个在线回归环境，个人适应回归模型：到达个人知道当前模型，并在战略上进行投资，以修改自己的功能，以提高当前模型分配给他们的预测分数。在各种情况下，已经观察到这种特征操纵 - 从信用评估到学校入学 - 对学习者提出了挑战。令人惊讶的是，我们发现这种战略操作实际上可能会帮助学习者恢复有意义的变量 - 即，在更改时会影响真正的标签的功能（与无效的非敏感功能相反）。我们表明，即使是学习者的简单行为，她也可以同时i）准确恢复有意义的功能，ii）激励代理人投资这些有意义的功能，从而激励了改进。
We consider an online regression setting in which individuals adapt to the regression model: arriving individuals are aware of the current model, and invest strategically in modifying their own features so as to improve the predicted score that the current model assigns to them. Such feature manipulation has been observed in various scenarios -- from credit assessment to school admissions -- posing a challenge for the learner. Surprisingly, we find that such strategic manipulations may in fact help the learner recover the meaningful variables -- that is, the features that, when changed, affect the true label (as opposed to non-meaningful features that have no effect). We show that even simple behavior on the learner's part allows her to simultaneously i) accurately recover the meaningful features, and ii) incentivize agents to invest in these meaningful features, providing incentives for improvement.
