动态增加量子线路深度，提升训练稳定性和泛化能力。
Quantum Circuit Training with Growth-Based Architectures
- 训练中逐步增加量子线路深度，自适应调整模型复杂度。
- 在回归与拉普拉斯方程任务中，损失更低且结果更稳定。
- 适合需要平衡表达力与鲁棒性的量子科学机器学习场景。
本研究提出基于增长的训练策略，通过在训练过程中逐步增加参数化量子电路（PQC）的深度，缓解过拟合并动态管理模型复杂度。我们设计了三种方法：模块增长、序列特征映射增长和交错特征映射增长，通过自适应添加重加载模块，扩展模型可覆盖的频率谱范围以响应训练需求。该方法使PQC在噪声环境中也能实现更稳定的收敛与泛化。我们在回归任务和二维拉普拉斯方程上进行评估，结果表明动态增长方法优于传统固定深度方案，最终损失更低，多次运行间方差更小。这些发现凸显了基于增长的PQC在量子科学机器学习（QSciML）中的潜力，尤其适用于需平衡表达力与稳定性的重要应用。
原文摘要 · Abstract (English)
This study introduces growth-based training strategies that incrementally increase parameterized quantum circuit (PQC) depth during training, mitigating overfitting and managing model complexity dynamically. We develop three distinct methods: Block Growth, Sequential Feature Map Growth, and Interleave Feature Map Growth, which add reuploader blocks to PQCs adaptively, expanding the accessible frequency spectrum of the model in response to training needs. This approach enables PQCs to achieve more stable convergence and generalization, even in noisy settings. We evaluate our methods on regression tasks and the 2D Laplace equation, demonstrating that dynamic growth methods outperform traditional, fixed-depth approaches, achieving lower final losses and reduced variance between runs. These findings underscore the potential of growth-based PQCs for quantum scientific machine learning (QSciML) applications, where balancing expressivity and stability is essential.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。