提出动态冻结策略优化量子神经网络，加速训练并克服平坦谷问题。
WSBD: Freezing-Based Optimizer for Quantum Neural Networks
- 根据梯度重要性动态冻结不关键参数，减少计算量
- 相比Adam平均快63.9%，且模型越大优势越明显
- 保持模型表达力，适合大规模量子神经网络训练
量子神经网络（QNN）的训练受梯度估计高成本和荒原悬崖问题（优化景观过度平坦）制约。为应对这些挑战，我们提出加权随机块下降（WSBD），一种具有参数级动态冻结策略的新优化器。WSBD通过梯度导出的重要度评分，智能识别并暂时冻结较不重要的参数，显著降低每步训练所需的前向传播次数，并更有效地导航优化空间。与剪枝或层冻结不同，WSBD在训练中持续调整，保持完整表达能力。大量评估显示，针对典型的基态能量问题，WSBD平均比Adam快63.9%收敛，优势随QNN规模增大而增强。我们提供了WSBD的严格收敛证明，表明参数级冻结优于传统层级方法。项目页面：https://github.com/Damrl-lab/WSBD-Stochastic-Freezing-Optimizer。
原文摘要 · Abstract (English)
The training of Quantum Neural Networks (QNNs) is hindered by the high computational cost of gradient estimation and the barren plateau problem, where optimization landscapes become intractably flat. To address these challenges, we introduce Weighted Stochastic Block Descent (WSBD), a novel optimizer with a dynamic, parameter-wise freezing strategy. WSBD intelligently focuses computational resources by identifying and temporarily freezing less influential parameters based on a gradient-derived importance score. This approach significantly reduces the number of forward passes required per training step and helps navigate the optimization landscape more effectively. Unlike pruning or layer-wise freezing, WSBD maintains full expressive capacity while adapting throughout training. Our extensive evaluation shows that WSBD converges on average 63.9% faster than Adam for the popular ground-state-energy problem, an advantage that grows with QNN size. We provide a formal convergence proof for WSBD and show that parameter-wise freezing outperforms traditional layer-wise approaches in QNNs. Project page: https://github.com/Damrl-lab/WSBD-Stochastic-Freezing-Optimizer.
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。