The limits of distribution-free conditional predictive inference
The limits of distribution-free conditional predictive inference
复制标题
DOI：
10.1093/imaiai/iaaa017
复制
发表时间：
2021-06-01
影响因子：
1.6
通讯作者：
Tibshirani, Ryan J.
中科院分区：
文献类型：
--
作者：
Barber, Rina Foygel;Candes, Emmanuel J.;Tibshirani, Ryan J.
我们考虑了无分配预测性推断的问题，其目的是产生预测覆盖范围，保证有条件而不是边缘地保持。诸如保形预测之类的现有方法提供边际覆盖范围保证，在所有可能的测试点中，预测性覆盖范围平均保持，但这对于许多实际应用不足，我们想知道我们的预测对给定个人有效，而不仅仅是仅仅是有效平均超过人口。另一方面，如果没有对基础分布施加假设，则已知确切的有条件推理保证是不可能的。在这项工作中，我们旨在探索这两者之间的空间，并研究有条件覆盖的属性的放松类型，可以减轻一些实际问题，并提供边际覆盖范围保证，同时仍然可以在无分配环境中实现。
We consider the problem of distribution-free predictive inference, with the goal of producing predictive coverage guarantees that hold conditionally rather than marginally. Existing methods such as conformal prediction offer marginal coverage guarantees, where predictive coverage holds on average over all possible test points, but this is not sufficient for many practical applications where we would like to know that our predictions are valid for a given individual, not merely on average over a population. On the other hand, exact conditional inference guarantees are known to be impossible without imposing assumptions on the underlying distribution. In this work, we aim to explore the space in between these two and examine what types of relaxations of the conditional coverage property would alleviate some of the practical concerns with marginal coverage guarantees while still being possible to achieve in a distribution-free setting.