arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.16623quant-ph
收藏

通过多层全连接变分量子电路实现可扩展的量子机器学习

Scalable Quantum Machine Learning via Multi-layer Fully-Connected Variational Quantum Circuits

Imperial College London(帝国理工学院);National Taiwan University(台湾大学);Brookhaven National Laboratory(布鲁克海文国家实验室)

Howard Su, Chen-Yu Liu, Samuel Yen-Chi Chen, Kuan-Cheng Chen, Huan-Hsin Tseng

AI总结:

本文提出多层全连接变分量子电路(FC-VQC),通过分解高维输入为固定大小的局部VQC块并用确定性块混合规则连接,实现参数可扩展的本地量子计算,提升量子机器学习性能。

摘要:

变分量子电路(VQC)是量子机器学习有前景的模型,但标准单体架构面临表达性与可训练性矛盾:小电路参数不足,大电路难以模拟和优化。我们提出多层全连接变分量子电路(FC-VQC),一种模块化框架,将高维输入分解为固定大小的局部VQC块,并通过确定性块混合规则连接。此设计保持每个量子计算本地化,同时允许可训练量子参数数量与输入维度线性增长。我们评估了FC-VQC在表格回归、表格分类和时空BSDE/PDE近似任务上的表现。在所有评估任务中,FC-VQC优于单体VQC基线,并在与结构匹配的深度神经网络(DNN)基线相比时达到竞争或更优性能,同时使用显著更少的可训练参数。

英文摘要:

Variational quantum circuits (VQCs) face an expressivity-trainability dilemma and scalability challenges. We propose Multi-Layer Fully-Connected Variational Quantum Circuits (FC-VQC), a general-purpose quantum machine learning framework that connects local VQC blocks through measurement, deterministic parameter-free routing, and re-encoding. All trainable model parameters reside within the quantum blocks, without trainable classical neural components. We study fully connected, sliding-window, and parallel block mixing and analyze computational costs, conditional error propagation, and block information exchange. Using classical simulation, we evaluate tabular regression and classification, with our main comparison addressing spatio-temporal function approximation for the Black--Scholes, Burgers, and time-dependent oscillatory PDEs with up to $144$ spatial dimensions. Comparisons include neural-network, explicit angle-feature, tensor-network, and gradient-boosted-tree baselines. The results show that FC-VQC achieves the lowest trajectory relative MAE for all PDEs at the higher dimensions $d\in\{81,144\}$. Gradient-dynamics and depolarizing-noise experiments provide complementary empirical diagnostics of trainability and preliminary noise sensitivity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑