arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.02435cs.GT
收藏

基于准确性拍卖的福利最优分类

Welfare-Optimal Classification with Accuracy Auctions

Technion(以色列理工学院);Caltech(加州理工学院)

Bana Sadi, Eden Saig, Nir Rosenfeld

AI总结:

提出一种结合真实性拍卖的学习算法,在用户对准确性估值私有的情况下优化社会福利,并给出高效计算分配和价格的方法。

摘要:

预测算法越来越多地被用于影响关于人类的决策,但最大化准确性——标准的学习目标——并不一定能最大化用户收益。相反,我们提出优化社会福利,定义为用户从正确预测中获得的平均收益。福利能够表达并因此考虑用户在准确性受益上的异质性。但由于这些估值是私有的,且用户可能通过虚报获益,学习必须同时 elicits 真实值并优化相对于这些值的福利。为此,我们提出一种结合真实性拍卖的新型学习算法。我们展示了如何高效计算分配和价格,并限制了付费用户的数量——令人惊讶的是,该数量与样本量无关。最后,我们在真实和合成数据上进行实验,展示了我们的算法,并探讨了福利与准确性之间的联系。

英文摘要:

Prediction algorithms are increasingly used to inform decisions about humans, but maximizing accuracy-the standard learning objective-is not necessarily optimal for this purpose. Instead, we propose optimizing social welfare, defined as the average gain users receive from correct predictions. Welfare enables to express, and therefore account for, heterogeneity in how much users benefit from accuracy. But since these valuations are private and users can benefit from overreporting them, learning must simultaneously elicit truthful values and optimize welfare with respect to them. To this end, we propose a novel learning algorithm that incorporates a truthful auction. We show how to compute allocations and prices efficiently, and bound the number of paying users-which surprisingly is independent of the sample size. We conclude with experiments on real and synthetic data that demonstrate our algorithm and explore the connections between welfare and accuracy.

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。

↑