利用光量子硬件噪声作为天然正则化，提升混合神经网络性能
PN-QNN: Harnessing Physical Noise as a Native Regularizer in Photonic Hybrid Quantum Neural Networks
- 将物理噪声引入光量子神经网络训练，以模拟类正则化效果
- 在鸢尾花和数字数据集上准确率提升0.82和1.45个百分点
- 噪声效果依赖数据集，不适用于所有任务，但可免费使用
近期内存量子硬件中的物理噪声通常被视为需抑制的干扰。本文探讨其是否可作为光子混合量子-经典神经网络（PHQCNN）的硬件原生正则化器，类似于经典深度学习中的噪声注入正则化。通过Quandela的Perceval仿真器与MerLin框架，我们在Iris、Digits和MNIST数据集上构建了PHQCNN，并直接将Perceval的七参数物理噪声模型注入训练过程。采用遗传算法搜索六个连续噪声维度和一个布尔参数，寻找每组数据集下最大化验证准确率的噪声配置，与无噪声基线在五个随机种子下对比。遗传算法优化后的噪声在Iris（+0.82pp）和Digits（+1.45pp）上带来小幅准确率提升，但在MNIST上导致明显下降（-1.21pp）。单参数扫描显示，任一单一噪声参数均无一致收益，支持联合优化；二阶损失展开表明，物理噪声诱导出类似Tikhonov的正则化项，其效果因数据集而异。因此，物理光子噪声可作为免费正则化器，但非普适有效。
原文摘要 · Abstract (English)
Physical noise in near-term quantum hardware is usually treated as a nuisance to suppress. We ask whether it can instead act as a hardware-native regularizer for photonic hybrid quantum-classical neural networks (PHQCNNs), analogous to noise-injection regularization in classical deep learning. Using Quandela's Perceval simulator and the MerLin framework, we build PHQCNNs for Iris, Digits, and MNIST and inject Perceval's seven-parameter physical noise model directly into training. A genetic algorithm searches the six continuous noise dimensions and 1 boolean parameter to find, per dataset, the configuration maximizing validation accuracy, compared against a noiseless baseline across five seeds. GA-tuned noise yields modest accuracy gains on Iris (+0.82pp) and Digits (+1.45pp), but a clear degradation on MNIST (-1.21pp). Per-parameter sweeps show that no individual noise parameter is consistently beneficial, motivating the joint search, while a second-order loss expansion shows that physical noise induces a Tikhonov-like regularization term whose effect is dataset-dependent. Physical photonic noise can thus act as a free regularizer, but not universally.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。