Conformalized Quantile Regression

TL;DR

This paper introduces a new adaptive conformalized quantile regression method that provides valid coverage and produces shorter prediction intervals by effectively handling heteroscedasticity in data.

Contribution

It combines conformal prediction with quantile regression to create a fully adaptive method that improves interval efficiency over existing conformal approaches.

Findings

Produces shorter, more efficient prediction intervals.

Maintains valid coverage guarantees.

Outperforms other conformal methods in experiments.

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.