发表机构
Florida Atlantic University; Khulna University of Engineering & Technology; Southern Illinois University Carbondale（佛罗里达大西洋大学; 库尔纳工程与技术大学; 南伊利诺伊大学卡本代尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对变分量子算法的贫瘠高原问题，提出Q-Capsule量子神经架构，通过多种技术缓解该问题，在分类任务上取得高准确率且减少两量子比特门使用量。
AI 中文摘要
变分量子算法常受限于贫瘠高原问题：随着量子电路规模和深度增加，梯度会消失，导致量子神经网络难以训练。我们提出Q-Capsule，一种基于局域化胶囊的量子神经架构，通过寄存器分区、局域读出、胶囊间稀疏耦合、可训练数据重上传以及量子费舍尔信息矩阵（QFIM）引导的自适应深度增长来缓解该问题。通过将每个可观测量的主导支撑限制在小型胶囊内并控制胶囊间纠缠，Q-Capsule在保留局域量子表示间通信的同时，维持有用的梯度信号。随着寄存器宽度增加，Q-Capsule始终保持稳定的梯度方差，而全局纠缠基线则呈现指数级抑制，每量子比特的对数梯度方差斜率接近-ln2。Q-Capsule还能产生更结构化的优化景观、更高的参数效率、更强的去极化噪声鲁棒性以及更低的测量需求。其自适应策略在二分类任务上达到98.1%的准确率，在四分类任务上达到97.7%，且在多分类任务中使用的两量子比特门数量比固定深度模型少约73%。
英文摘要
Variational quantum algorithms are often limited by barren plateaus: gradients vanish as circuit size and depth increase, making quantum neural networks difficult to train. We propose Q-Capsule, a localized capsule-based quantum neural architecture that mitigates this problem through register partitioning, local readout, sparse inter-capsule coupling, trainable data re-uploading, and Quantum Fisher Information Matrix (QFIM)-guided adaptive depth growth. By restricting the dominant support of each observable to a small capsule and controlling inter-capsule entanglement, Q-Capsule preserves useful gradient signals while retaining communication between local quantum representations. As the register width increases, Q-Capsule consistently maintains stable gradient variance, whereas globally entangling baselines exhibit exponential suppression with a log-gradient-variance slope near -ln 2 per qubit. Q-Capsule also produces more structured optimization landscapes, higher parameter efficiency, improved robustness to depolarizing noise, and lower measurement requirements. Its adaptive policy achieves 98.1% accuracy on binary classification and 97.7% on four-class classification, while using approximately 73% fewer two-qubit gates than the fixed-deep model on the multiclass task.
