Towards Noise-Resilient Quantum Multi-Armed and Stochastic Linear Bandits

TL;DR

This paper develops noise-robust quantum algorithms for multi-armed and stochastic linear bandits, improving estimation accuracy and regret in noisy quantum environments, thus making quantum speedups more practical on current NISQ devices.

Contribution

It introduces a noise-robust quantum Monte Carlo estimator and extends it to quantum bandit algorithms, addressing noise issues in NISQ devices and maintaining quantum advantages.

Findings

Improved estimation accuracy under quantum noise models

Reduced regret in noisy quantum bandit algorithms

Demonstrated robustness on NISQ hardware simulations

Abstract

Quantum multi-armed bandits (MAB) and stochastic linear bandits (SLB) have recently attracted significant attention, as their quantum counterparts can achieve quadratic speedups over classical MAB and SLB. However, most existing quantum MAB algorithms assume ideal quantum Monte Carlo (QMC) procedures on noise-free circuits, overlooking the impact of noise in current noisy intermediate-scale quantum (NISQ) devices. In this paper, we study a noise-robust QMC algorithm that improves estimation accuracy when querying quantum reward oracles. Building on this estimator, we propose noise-robust QMAB and QSLB algorithms that enhance performance in noisy environments while preserving the advantage over classical methods. Experiments show that our noise-robust approach improves QMAB estimation accuracy and reduces regret under several quantum noise models.