Majority vote ensembles of conformal predictors

作者:Giovanni Cherubin

摘要

We study majority vote ensembles of \(\varepsilon \)-valid conformal predictors (CP). We show that the prediction set \(\varGamma ^\eta \) produced as the majority vote among the prediction sets \(\varGamma ^\varepsilon _i\) of k independent \(\varepsilon \)-valid CPs is also valid, for some significance level \(\eta \); we provide a method to compute \(\varepsilon \) to achieve a desired \(\eta \). We further indicate an error upper bound for an ensemble of correlated CPs, and derive a value \(\varepsilon \) for which such an ensemble guarantees \(\eta \) conservative validity. We evaluate empirically our findings, and compare them with alternative strategies for combining CPs’ predictions.

论文关键词:Conformal prediction, Ensembles, Majority vote, Error bounds

论文评审过程:

论文官网地址:https://doi.org/10.1007/s10994-018-5752-y