Online Localized Conformal Prediction

TL;DR

This paper introduces Online Localized Conformal Prediction (OLCP), a method that adapts to covariate heterogeneity in online settings, providing valid uncertainty quantification with narrower prediction sets.

Contribution

It proposes OLCP and OLCP-Hedge, novel algorithms that incorporate covariate-dependent localization and bandwidth selection for improved online conformal prediction.

Findings

OLCP achieves valid long-run coverage in online settings.

OLCP-Hedge effectively selects localization bandwidths online.

Proposed methods produce narrower prediction sets than existing baselines.

Abstract

Conformal prediction is a framework that provides valid uncertainty quantification for general models with exchangeable data. However, in the online learning and time-series settings, exchangeability is not satisfied. Existing online conformal methods, such as adaptive conformal inference (ACI), can achieve long-run validity, yet they remain inefficient under covariate heterogeneity because they rely on global calibration. We propose \emph{Online Localized Conformal Prediction (OLCP)}, which combines online adaptation with covariate-dependent localization to better reflect heterogeneity. To reduce sensitivity to the localization bandwidth, we further develop \emph{OLCP-Hedge}, which performs bandwidth selection as an online expert aggregation problem using a constrained online convex optimization framework. Importantly, we provide coverage guarantees for both algorithms and demonstrate through simulations and real-data experiments that the proposed methods attain valid long-run coverage with narrower prediction sets than existing baselines.