arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08507cs.LGcs.DSmath.STstat.TH
收藏

多重校准的范围:通过属性获取表征多重校准

The Scope of Multicalibration: Characterizing Multicalibration via Property Elicitation

University of Pennsylvania(宾夕法尼亚大学)

Georgy Noarov, Aaron Roth

摘要:

我们之间的连接多校准和属性引出,并表明(在温和的技术条件下),它是可能的,以产生一个多校准的预测连续标量分布属性$Γ$当且仅当$Γ$是引出。在消极的一面,我们表明,对于非引出的连续属性,存在简单的数据分布,即使是真正的分布预测没有校准。从积极的方面来说,对于可引发的$Γ$,我们为批量和在线对抗设置提供了简单的规范算法,该算法学习$Γ$ -多校准预测器。这概括了过去对多校准均值和分位数的工作,实际上加强了现有的在线分位数多校准结果。为了进一步抵消我们的负面结果,我们表明,如果一个属性$Γ^1$本身是不引出的,但引出另一个引出的属性$Γ^0$的条件,然后有一个典型的算法,共同多校准$Γ^1$和$Γ^0$,这概括了过去的平均时刻多校准的工作。最后,作为我们理论的应用,我们为公平(多校准)风险评估提供了新的算法和不可能的结果。

英文摘要:

We make a connection between multicalibration and property elicitation and show that (under mild technical conditions) it is possible to produce a multicalibrated predictor for a continuous scalar distributional property $Γ$ if and only if $Γ$ is elicitable. On the negative side, we show that for non-elicitable continuous properties there exist simple data distributions on which even the true distributional predictor is not calibrated. On the positive side, for elicitable $Γ$, we give simple canonical algorithms for the batch and the online adversarial setting, that learn a $Γ$-multicalibrated predictor. This generalizes past work on multicalibrated means and quantiles, and in fact strengthens existing online quantile multicalibration results. To further counter-weigh our negative result, we show that if a property $Γ^1$ is not elicitable by itself, but is elicitable conditionally on another elicitable property $Γ^0$, then there is a canonical algorithm that jointly multicalibrates $Γ^1$ and $Γ^0$; this generalizes past work on mean-moment multicalibration. Finally, as applications of our theory, we provide novel algorithmic and impossibility results for fair (multicalibrated) risk assessment.

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。

↑