$\Psi$ 的桥：基于薛定谔桥的量子电路优化
Bridge of $Ψ$'s: Quantum Circuit Optimization with Schrödinger Bridges
浏览论文内容
中文总结 AI 辅助
提出基于薛定谔桥的生成模型BOPS，直接从示例学习量子电路优化，在8量子比特×64深度Clifford+T电路上实现门数2.46倍和深度2.45倍的缩减，优于九个基线优化器。
中文摘要 AI 辅助
量子电路优化将电路替换为门数更少、深度更低的等效电路，从而降低执行成本和错误率。我们提出一个问题：生成模型能否直接从示例中学习这种变换，而不是从固定的重写库或僵化的代数例程中选择。我们提出了 $\Psi$ 的桥（BOPS），一种基于薛定谔桥的生成模型，采用自定义去噪器架构，学习从源电路到等效优化电路的变换。我们在为现有优化器构造的困难数据上训练该模型，通过反向应用重写规则，使每个输入都有已知的低成本目标。在保留的8量子比特×64深度Clifford+$T$电路上，BOPS在几何平均上将门数减少$2.46\times$，深度减少$2.45\times$，优于所有九个基线优化器。这构成了首个连接量子电路与前沿机器学习方法的生成模型，沿多个轴打开了量子编译栈的 learned optimization 之门。
英文摘要
Quantum circuit optimization replaces a circuit with an equivalent one of fewer gates and lower depth, reducing execution cost and error rate. We ask whether a generative model can learn this transformation directly from examples, rather than selecting from a fixed rewrite library or rigid algebraic routines. We present Bridge of $Ψ$'s (BOPS), a generative model based on Schrödinger bridges, using a custom denoiser architecture, that learns a transformation from a source circuit into an equivalent optimized circuit. We train it on data constructed to be hard for existing optimizers, by applying rewrite rules backwards so that each input has a known lower-cost target. On held-out 8 qubits $\times$ 64 depth Clifford+$T$ circuits, BOPS reduces gate count by $2.46\times$ and depth by $2.45\times$ in geometric mean, outperforming all nine baseline optimizers. This constitutes the first generative model bridging quantum circuits and frontier machine learning methods, opening up the quantum compilation stack to learned optimization along multiple axes.
发表机构
- ETH Zürich（苏黎世联邦理工学院）
- University of Cambridge（剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。
