arXiv：cs.LG· Awal Ahmed Fime, Tasfia Zaman Samiha, Saika Zaman, Dimitris Pados, George Sklivanitis, Abdur R. Shahid, Ahmed Imteaj·· 3 小时前
Q-Capsule：用于缓解贫瘠高原的局部化胶囊量子神经架构
Q-Capsule: A Localized Capsule-Based Quantum Neural Architecture for Barren Plateau Mitigation
AI 导读
研究者提出 Q-Capsule 局部化胶囊量子神经架构，通过寄存器分区、局部读出、稀疏胶囊间耦合、可训练数据重上传和 QFIM 引导的自适应深度增长缓解贫瘠高原问题。
正文
Abstract: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.
| Subjects: | Quantum Physics (quant-ph); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.11261 [quant-ph] |
| (or arXiv:2610.11261v1 [quant-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11261 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ahmed Imteaj [view email]
[v1]
Thu, 8 Oct 2026 05:14:48 UTC (5,561 KB)
来源：arXiv：cs.LG · arxiv.org