We present a general, efficient technique for providing contextual predictions that are "multivalid" in various senses, against an online sequence of adversarially chosen examples $(x,y)$. This means that the resulting estimates correctly predict various statistics of the labels $y$ not just marginally -- as averaged over the sequence of examples -- but also conditionally on $x \in G$ for any $G$ belonging to an arbitrary intersecting collection of groups $\mathcal{G}$. We provide three instantiations of this framework. The first is mean prediction, which corresponds to an online algorithm satisfying the notion of multicalibration from Hebert-Johnson et al. The second is variance and higher moment prediction, which corresponds to an online algorithm satisfying the notion of mean-conditioned moment multicalibration from Jung et al. Finally, we define a new notion of prediction interval multivalidity, and give an algorithm for finding prediction intervals which satisfy it. Because our algorithms handle adversarially chosen examples, they can equally well be used to predict statistics of the residuals of arbitrary point prediction methods, giving rise to very general techniques for quantifying the uncertainty of predictions of black box algorithms, even in an online adversarial setting. When instantiated for prediction intervals, this solves a similar problem as conformal prediction, but in an adversarial environment and with multivalidity guarantees stronger than simple marginal coverage guarantees.
翻译:我们提出了一个通用的、有效的技术,用来提供“多重价值”的各种背景预测,以对抗性选择的在线实例(x,y)美元为在线序列。这意味着,由此得出的估计正确地预测了各种标签的统计,其中美元不仅是微不足道的 -- -- 与实例序列相比的平均数 -- -- 而且还以美元为条件,作为属于任意交叉收集的集团($\mathcal{G}$)的任何G$为条件。我们提供了三个对这个框架的回想。第一个是平均预测,它与满足Hebert-Johnson等人的多点调整概念的在线算法相对应。第二个是差异和更高时刻的预测,它相当于一种在线算法,它满足了条件平均时间多点的多点调整概念。最后,我们定义了一个预测间隔的新的概念,为找到能够满足它的预测间隔提供了一种算法。因为我们的算法处理敌对性选择的例子,它们同样可以用来预测甚至任意点预测方法的剩余数据,从而形成一种非常普遍的预测性预测性预测,从而产生一种非常普遍的预测性的预测性的方法,用来量化这种预测的不稳定性,作为一种简单的预测的精确的预测,作为一种比较的精确的预测的预测,作为一种比较的精确的预测的保证,一种比较的预测,作为一种比较的精确的保证,作为一种比较的预测的一种,在一种比较的精确的预测的一种,在一种比较的基中的一种,在一种比较的精确的预测的一种,在一种比较中的一种,在一种比较的预测的一种,在一种比较的精确的精确的保证。