Conformalized Quantile Regression

Code

• github.com/yromano/cqr
  OfficialIn paperpytorch★ 0
• github.com/lightning-uq-box/lightning-uq-box
  pytorch★ 217
• github.com/yromano/fair_dummies
  pytorch★ 3
• github.com/yongsukyee/uncertain_blackholemass
  pytorch★ 2
• github.com/chancejohnstone/piRF
  none★ 0

Abstract

Conformal prediction is a technique for constructing prediction intervals that attain valid coverage in finite samples, without making distributional assumptions. Despite this appeal, existing conformal methods can be unnecessarily conservative because they form intervals of constant or weakly varying length across the input space. In this paper we propose a new method that is fully adaptive to heteroscedasticity. It combines conformal prediction with classical quantile regression, inheriting the advantages of both. We establish a theoretical guarantee of valid coverage, supplemented by extensive experiments on popular regression datasets. We compare the efficiency of conformalized quantile regression to other conformal methods, showing that our method tends to produce shorter intervals.

Tasks

Reproductions