发表机构
Centre for Computational Science, University College London; Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities（计算科学中心，伦敦大学学院; 巴伐利亚科学院和人文科学莱比锡超算中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对物理系统机器学习替代模型的矛盾，提出量子压缩机器学习，通过压缩潜在传播器参数解决问题，该方法在心血管基准测试中表现良好，确立了其在科学机器学习及实际量子优势方面的地位。
AI 中文摘要
物理系统的机器学习替代模型面临一个悖论：可解释模型在捕捉复杂非线性流动时面临表现力挑战，而富有表现力的深度替代模型仅通过大量参数化来匹配高保真模拟，这使得学习到的动力学变成黑箱。本文引入量子压缩机器学习（QCML），通过将流动替代模型的潜在传播器从524,288个可训练参数压缩到不超过8个来解决这一矛盾。这种参数减少使学习到的动力学定律达到物理本构关系的参数规模，使替代模型无需牺牲表现力即可直接解释和控制。压缩通过结构化量子电路实现，其酉传播器将潜在频谱精确约束到单位圆，通过自回归展开用线性积累代替指数误差增长。经典正则化只能近似这种约束，而QCML在整个展开过程中保持稳定。在两个特定患者的心血管基准测试中，结构化QCML传播器在表面压力谱、压降和壁面剪应力方面与经典对应物的预测精度相当。这些结果确立了QCML作为科学机器学习的一个有效组成部分以及对实际世界预测中实际量子优势的具体贡献。
英文摘要
Machine-learning surrogates of physical systems face a paradox: explainable models facing the challenge of expressivity to capture complex nonlinear flows, whereas expressive deep surrogates match high-fidelity simulations only through massive parameterisations that turn the learned dynamics into a black box. Here, we introduce quantum-compressed machine learning (QCML), which resolves this tension by compressing the latent propagator of a flow surrogate from $524{,}288$ trainable parameters to no more than $8$. This parameter reduction brings the learned dynamical law to the parameter scale of a physical constitutive relation rather than a black-box neural network, making the surrogate directly interpretable and controllable without sacrificing expressivity. The compression is realised by a structured quantum circuit whose unitary propagator constrains the latent spectrum to the unit circle exactly and by construction, replacing exponential error growth with linear accumulation over autoregressive rollouts. Classical regularisation only approximates this constraint: even a quantum-inspired classical baseline penalised towards unitarity collapses within one Lyapunov time on turbulent channel flow, whereas QCML remains stable over the full rollout. Shared phase and coupling angles parameterising the circuit correspond directly to modal frequencies and inter-mode interactions, giving the learned dynamics a physical interpretation in spectral space. On two patient-specific cardiovascular benchmarks, the structured QCML propagator matches the predictive accuracy of its classical counterpart on surface pressure spectra, pressure drop, and wall shear stress. These results establish QCML as a working component of scientific machine learning and a concrete contribution towards practical quantum advantage in real-world prediction.
