Distribution-Free Prediction Sets for Two-Layer Hierarchical Models
Distribution-Free Prediction Sets for Two-Layer Hierarchical Models
复制标题
两层分层模型的无分布预测集
DOI：
10.1080/01621459.2022.2060112
复制
发表时间：
2018
影响因子：
3.7
通讯作者：
Aaditya Ramdas
中科院分区：
文献类型：
--
作者：
Robin Dunn;L. Wasserman;Aaditya Ramdas
摘要考虑了两层分层分布数据的无分布预测集的构造问题。对于iid数据，可以使用保角预测的方法来构造预测集。适形预测的有效性取决于数据的交换，当观察组来自不同的分布时，如医学数据库中每个患者的多个观察结果，这就不成立了。我们扩展共形方法的层次设置。我们开发了CDF池，单次抽样和重复抽样方法来构建无监督和监督设置中的预测集。我们比较这些方法的覆盖范围和平均集大小。如果渐近覆盖率是可以接受的，我们建议CDF池化，因为它在经验覆盖率和平均集大小之间取得了平衡。如果我们想要覆盖保证，那么我们推荐重复子采样方法。本文的补充材料可在网上查阅。
Abstract We consider the problem of constructing distribution-free prediction sets for data from two-layer hierarchical distributions. For iid data, prediction sets can be constructed using the method of conformal prediction. The validity of conformal prediction hinges on the exchangeability of the data, which does not hold when groups of observations come from distinct distributions, such as multiple observations on each patient in a medical database. We extend conformal methods to a hierarchical setting. We develop CDF pooling, single subsampling, and repeated subsampling approaches to construct prediction sets in unsupervised and supervised settings. We compare these approaches in terms of coverage and average set size. If asymptotic coverage is acceptable, we recommend CDF pooling for its balance between empirical coverage and average set size. If we desire coverage guarantees, then we recommend the repeated subsampling approach. Supplementary materials for this article are available online.
影响因子：
1.6
作者：
Barber, Rina Foygel;Candes, Emmanuel J.;Tibshirani, Ryan J.
通讯作者：
Tibshirani, Ryan J.
用于高效分布的离散共形预测——自由推理
影响因子：
1.7
作者：
Chen, Wenyu;Chun, Kelli‐Jean;Barber, Rina Foygel
通讯作者：
Barber, Rina Foygel
影响因子：
4.5
作者：
Barber, Rina Foygel;Candes, Emmanuel J.;Tibshirani, Ryan J.
通讯作者：
Tibshirani, Ryan J.