学习排序张量网络收缩计划以实现GPU加速的量子电路模拟

中文摘要 AI 辅助

经典模拟对于量子算法的开发与验证仍至关重要，但其成本会随电路规模增大而快速增长。张量网络收缩可通过利用电路结构降低该成本，不过其效率高度依赖所选的收缩计划。在GPU上，理论复杂度相似的计划性能可能差异显著，因为执行表现还取决于并行度、归约结构、内存访问量及收缩几何结构。我们提出一种学习排序框架，用于在执行收缩计划前选择高效的计划。每个计划由直接从其成对收缩序列导出的结构特征表示，梯度提升排序器通过列表式和成对式目标函数，基于GPU测量数据进行训练。我们在多种电路族上评估所得模型，使用同分布测试集和电路族偏移测试集，并将其与随机基线及基于MinFill的基线对比。学习得到的排序器通常能识别更优的计划，其中列表式模型提供最强的整体决策质量。我们还研究后端偏移，对比两种GPU架构上的经验计划排序，并在未重新训练的情况下，将源训练模型在第二个设备上评估。不同GPU间的排序虽非完全一致，但仍保持显著稳定性，且模型仍具备实用的决策质量。这些结果表明，学习排序是减少收缩计划搜索的实用方法，同时也显示性能部分依赖于后端。

英文摘要

Classical simulation remains essential for developing and validating quantum algorithms, but its cost grows rapidly with circuit size. Tensor-network contraction can reduce this cost by exploiting circuit structure, although its efficiency depends strongly on the chosen contraction plan. On GPUs, plans with similar theoretical complexity may perform very differently because execution also depends on parallelism, reduction structure, memory traffic, and contraction geometry. We present a learning-to-rank framework for selecting efficient contraction plans before executing them. Each plan is represented by structural features derived directly from its sequence of pairwise contractions, and gradient-boosted rankers are trained from GPU measurements using listwise and pairwise objectives. We evaluate the resulting models on diverse circuit families, using separate in-distribution and circuit-family-shift test sets, and compare them with random and MinFill-based baselines. The learned rankers generally identify better plans, with the listwise model providing the strongest overall decision quality. We also study backend shift by comparing empirical plan orderings on two GPU architectures and evaluating the source-trained models on the second device without retraining. The rankings remain substantially, though not perfectly, stable across GPUs, and the models retain useful decision quality. These results support Learning to Rank as a practical way to reduce contraction-plan search, while showing that performance remains partly backend dependent.

发表机构

• Universitat de València（瓦伦西亚大学）
• Universitat Jaume I（哈梅一世大学）

机构由 AI 辅助整理，请以论文原文为准。