发表机构
ICB, UTBM; SINERGIES (UR 4662), UMLP; LAMMA, Universite de Lomé（贝尔福-蒙贝利亚尔技术大学 ICB; UMLP SINERGIES（UR 4662）; 洛美大学 LAMMA）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出混合变分量子电路，结合经典仿射层实现高效多元回归，理论证明其逼近能力，实验在图像重建和Friedman1基准上媲美高斯过程回归并优于XGBoost和随机森林。
AI 中文摘要
变分量子电路（VQCs）是通过经典方式优化的参数化量子电路。我们提出了一种混合变分量子电路（HVQC），通过引入经典仿射后测量层扩展了VQCs，从而无需独立标量电路的线性开销即可实现向量值回归。理论上，我们证明了基本的单量子比特和双量子比特电路可以通过数据重上传和纠缠来逼近二次函数和乘积，为完整架构提供了基础。实验上，在两个合成图像重建数据集和Friedman1基准（40,568个测试样本）上，我们的HVQC与高斯过程回归相当，并优于XGBoost和随机森林。消融研究证实了量子与经典组件均不可或缺，结果凸显了特征映射在混合量子-经典模型中的核心作用。
英文摘要
Variational quantum circuits (VQCs) are parameterized quantum circuits optimized classically. We propose a hybrid variational quantum circuit (HVQC) extending VQCs with a classical affine post-measurement layer, enabling vector-valued regression without the linear overhead of independent scalar circuits. Theoretically, we show that elementary one-and two-qubit circuits can approximate quadratic functions and products via data re-uploading and entanglement, providing the foundations of the full architecture. Experimentally, on two synthetic image reconstruction datasets and the Friedman1 benchmark (40,568 test samples), our HVQC matches Gaussian Process Regression and outperforms XGBoost and Random Forest. An ablation study confirms that both quantum and classical components are essential, and results highlight the central role of the feature map in hybrid quantum-classical models.
Journal refThe Seventeenth International Conference on Information, Intelligence, Systems and Applications (IISA 2026), Jul 2026, Rhodes Island, Greece, Greece
