Conformalized Quantile Regression
This work addresses the need for more efficient and adaptive prediction intervals in regression tasks, particularly for applications requiring reliable uncertainty estimates, though it is an incremental improvement over existing conformal methods.
The paper tackled the problem of constructing prediction intervals that are valid in finite samples without distributional assumptions, but existing methods were often overly conservative with constant or weakly varying interval lengths. The result was a new method combining conformal prediction with quantile regression, which achieved valid coverage and produced shorter intervals in experiments on popular regression datasets.
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.