Pulsed learning for quantum data re-uploading models

TL;DR

This paper introduces a pulse-based data re-uploading model for quantum machine learning, demonstrating improved performance and noise resilience on simulated NISQ hardware compared to traditional gate-based methods.

Contribution

It formulates a novel pulse-level data re-uploading approach and benchmarks it, showing superior accuracy and robustness under realistic noise conditions.

Findings

Pulse-based models outperform gate-based counterparts in accuracy.

Pulse models exhibit higher resilience to noise and decoherence.

Pulse implementations maintain higher fidelity as noise increases.

Abstract

While Quantum Machine Learning (QML) holds great potential, its practical realization on Noisy Intermediate-Scale Quantum (NISQ) hardware has been hindered by the limitations of variational quantum circuits (VQCs). Recent evidence suggests that VQCs suffer from severe trainability and noise-related issues, leading to growing skepticism about their long-term viability. However, the possibility of implementing learning models directly at the pulse-control level remains comparatively unexplored and could offer a promising alternative. In this work, we formulate a pulse-based variant of data re-uploading, embedding trainable parameters directly into the native system's dynamics. We benchmark our approach on a simulated superconducting transmon processor with realistic noise profiles. The pulse-based model consistently outperforms its gate-based counterpart, exhibiting higher test accuracy and improved generalization under equivalent noise conditions. Moreover, by systematically increasing noise strength, we show that pulse-level implementations retain higher fidelity for longer, demonstrating enhanced resilience to decoherence and control errors. These results suggest that pulse-native architectures, though less explored, may offer a viable and hardware-aligned path forward for practical QML in the NISQ era.