Adaptive Conformal Prediction for Quantum Machine Learning

TL;DR

This paper introduces Adaptive Quantum Conformal Prediction (AQCP), a method that maintains reliable uncertainty quantification in quantum machine learning despite hardware noise, demonstrated on IBM quantum processors.

Contribution

It formalizes how quantum noise affects conformal guarantees and proposes AQCP, a novel algorithm ensuring asymptotic coverage under noisy conditions.

Findings

AQCP achieves target coverage levels in experiments.

AQCP exhibits greater stability than existing quantum conformal prediction.

The method maintains validity despite arbitrary hardware noise.

Abstract

Quantum machine learning seeks to leverage quantum computers to improve upon classical machine learning algorithms. Currently, robust uncertainty quantification methods remain underdeveloped in the quantum domain, despite the critical need for reliable and trustworthy predictions. Recent work has introduced quantum conformal prediction, a framework that produces prediction sets that are guaranteed to contain the true outcome with a user-specified probability. In this work, we formalise how the time-varying noise inherent in quantum processors can undermine conformal guarantees, even when calibration and test data are exchangeable. To address this challenge, we draw on Adaptive Conformal Inference, a method which maintains validity over time via repeated recalibration. We introduce Adaptive Quantum Conformal Prediction (AQCP), an algorithm which provides asymptotic average coverage guarantees under arbitrary hardware noise conditions. Empirical studies on an IBM quantum processor demonstrate that AQCP achieves the target coverage level and exhibits greater stability than quantum conformal prediction.