Robust Validation: Confident Predictions Even When Distributions Shift

TL;DR

This paper introduces a conformal inference method that provides reliable uncertainty estimates for predictions even when test data distributions differ from training data, by estimating and accounting for potential distribution shifts.

Contribution

It develops a novel approach for robust predictive inference that guarantees coverage under distributional shifts using conformal methods and shift estimation.

Findings

Achieves nearly valid coverage in finite samples.

Effectively estimates and accounts for distribution shifts.

Demonstrates robustness on large-scale benchmark datasets.

Abstract

While the traditional viewpoint in machine learning and statistics assumes training and testing samples come from the same population, practice belies this fiction. One strategy -- coming from robust statistics and optimization -- is thus to build a model robust to distributional perturbations. In this paper, we take a different approach to describe procedures for robust predictive inference, where a model provides uncertainty estimates on its predictions rather than point predictions. We present a method that produces prediction sets (almost exactly) giving the right coverage level for any test distribution in an $f$-divergence ball around the training population. The method, based on conformal inference, achieves (nearly) valid coverage in finite samples, under only the condition that the training data be exchangeable. An essential component of our methodology is to estimate the amount of expected future data shift and build robustness to it; we develop estimators and prove their consistency for protection and validity of uncertainty estimates under shifts. By experimenting on several large-scale benchmark datasets, including Recht et al.'s CIFAR-v4 and ImageNet-V2 datasets, we provide complementary empirical results that highlight the importance of robust predictive validity.