发表机构
Shanghai Maritime University; Agency for Science, Technology and Research (A*STAR); Singapore Institute of Technology; Singapore Management University (SMU); Columbia University; Tongji University（上海海事大学; 新加坡科技研究局; 新加坡理工学院; 新加坡管理大学; 哥伦比亚大学; 同济大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有QGAN基于块分解导致全局一致性弱和资源开销大的问题，提出BasicQGAN，通过校准量子先验诱导的量子保真度景观，实现单电路端到端像素级图像生成，所需量子比特和参数更少且性能更优。
AI 中文摘要
量子生成对抗网络（QGAN）已成为含噪声中等规模量子（NISQ）时代具有代表性的生成模型，并在量子机器学习领域引起了越来越多的关注。然而，现有的大多数QGAN方法依赖于基于块的分解策略，这削弱了生成图像的全局一致性，并增加了量子资源开销。在本工作中，我们研究了一种更简单的方法：使用单量子电路QGAN进行像素级端到端图像生成。通过分析希尔伯特空间中量子先验与目标数据分布之间的结构匹配关系，我们为理解朴素端到端QGAN的训练行为提供了新的理论视角。具体而言，我们引入了量子保真度景观（QFL），定义为由量子态系综诱导并在量子生成过程的共享酉变换下保持的成对保真度结构。我们证明，在固定的Lipschitz读出下，该不变量对解码后的样本分离施加了单侧界限，这促使在对抗训练之前对先验诱导的QFL进行校准。为验证这一理论见解，我们提出了BasicQGAN，一种包含量子先验校准的QGAN框架。在对抗优化之前，BasicQGAN将先验诱导的QFL与数据诱导的QFL对齐。在小规模灰度图像数据集上的实验结果表明，BasicQGAN实现了稳定有效的端到端像素级图像生成，同时相比代表性的基于块的量子生成器，所需的量子比特和可训练参数更少。此外，使用不同初始量子态系综的实验表明，经QFL校准的系综获得了更好的生成性能。
英文摘要
Quantum Generative Adversarial Networks (QGANs) have emerged as representative generative models in the Noisy Intermediate-Scale Quantum (NISQ) era and have attracted increasing attention in quantum machine learning. However, most existing QGAN methods rely on patch-based decomposition strategies, which weaken the global consistency of generated images and increase quantum resource overhead. In this work, we investigate a simpler approach: pixel-level, end-to-end image generation using a single-quantum-circuit QGAN. By analyzing the structural matching relationship between the quantum prior and the target data distribution in Hilbert space, we provide a new theoretical perspective for understanding the training behavior of naive end-to-end QGANs. Specifically, we introduce the Quantum Fidelity Landscape (QFL), defined as the pairwise-fidelity structure induced by an ensemble of quantum states and preserved under shared unitary transformations of the quantum generation process. We show that, under a fixed Lipschitz readout, this invariant imposes a one-sided bound on decoded sample separation, motivating calibration of the prior-induced QFL before adversarial training. To validate this theoretical insight, we propose BasicQGAN, a QGAN framework incorporating quantum prior calibration. Before adversarial optimization, BasicQGAN aligns the prior-induced QFL with the data-induced QFL. Experimental results on small-scale grayscale image datasets show that BasicQGAN achieves stable and effective end-to-end pixel-level image generation while requiring fewer qubits and trainable parameters than representative patch-based quantum generators. Furthermore, experiments with different initial quantum-state ensembles show that QFL-calibrated ensembles achieve better generative performance.
