arXiv：cs.LG· Tao Liu, Ge He, Dongyu Liang, Wujie Wen·· 2 天前AI 评分27
混合量子-经典模型能否预测降阶脑变形动力学？arXiv 基准评测
Evaluating Hybrid Quantum-Classical Models for Reduced-Order Brain Deformation Dynamics
AI 导读
一项 arXiv 研究用 POD 将高维脑变形位移场投影到紧凑潜空间，系统评测混合量子-经典模型与经典基线在静态回归和自回归预测两类任务上的表现。结果显示经典 POD-MLP 在静态回归中优于所有量子变体，经典 POD-LSTM 在不同历史窗口和随机初始化下也比增强版 QLSTM 更准确、更稳定。研究认为降阶物理场学习可作为近期量子机器学习的严格测试平台。
正文
Abstract:We evaluate hybrid quantum-classical machine learning for the reduced-order prediction of spatiotemporal brain deformation fields. To mitigate the computational intractability of high-dimensional displacement fields, we employ Proper Orthogonal Decomposition (POD) to project the data into a compact latent space. Within this framework, we formulate two distinct learning objectives: static temporal-to-latent regression and autoregressive latent state forecasting. We systematically benchmark compact classical baselines against both minimal and enhanced hybrid quantum architectures. Our results demonstrate that classical networks provide the strongest baselines in the present setting. For static regression, a classical POD-MLP outperforms all evaluated quantum variants, although an enhanced Variational Quantum Circuit (VQC) substantially improves upon a minimal VQC baseline. For temporal forecasting, a classical POD-LSTM delivers superior predictive accuracy and statistical robustness compared to an enhanced Quantum LSTM (QLSTM) across varying history windows and random initializations. Overall, this study establishes reduced-order physical field learning as a rigorous testbed for near-term QML, highlighting that while hybrid enhancements successfully recover expressivity in weak quantum circuits, classical architectures retain a definitive advantage in both fidelity and stability.
| Comments: | QCE26 |
| Subjects: | Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2610.00554 [cs.LG] |
| (or arXiv:2610.00554v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00554 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tao Liu [view email]
[v1]
Wed, 30 Sep 2026 18:29:46 UTC (6,557 KB)
来源：arXiv：cs.LG · arxiv.org