Fast conformal classification using influence functions

Fast conformal classification using influence functions
复制标题

使用影响函数进行快速共形分类

DOI:
--
复制
发表时间:
2021
期刊:
International Symposium on Conformal and Probabilistic Prediction with Applications
影响因子:
--
通讯作者:
Giovanni Cherubin
Giovanni Cherubin
中科院分区:
--
文献类型:
--
作者:
Umang Bhatt;Adrian Weller;Giovanni Cherubin

文献摘要

参考文献

被引文献

相似文献

我们使用鲁棒统计中的自适应函数来加速完全保形预测。传统上,保形预测需要重新训练多个留一分类器来计算每个测试点的p值。通过使用插值函数,我们能够近似这个过程,并大大加快了时间复杂度
We use influence functions from robust statistics to speed up full conformal prediction. Traditionally, conformal prediction requires retraining multiple leave-one-out classifiers to calculate p-values for each test point. By using influence functions, we are able to approximate this procedure and to speed up considerably the time complexity
DOI: 10.1214/20-aos1965
发表时间: 2021-02-01
影响因子: 4.5
作者:
Barber, Rina Foygel;Candes, Emmanuel J.;Tibshirani, Ryan J.
通讯作者: Tibshirani, Ryan J.