干涉何时有助于学习？核几何作为光子储备池计算的预实验测试
When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing
浏览论文内容
中文总结 AI 辅助
该研究通过玻色采样特征图的核几何，证明多光子干涉可产生核几何分离，为光子储备池计算提供了预实验测试协议，调和了现有实验结果并明确了干涉对学习的作用条件。
中文摘要 AI 辅助
多光子干涉是光子量子机器学习最原生的资源，但光子储备池的实验却报告了优势、无效结果和仅训练效应，这些结果无法直接比较，因为每项研究都在不同任务和平台上测量任务相关的准确率。本文通过玻色采样特征图的核几何，独立于任务解决该问题：干涉在约两倍于可区分粒子统计的有效维度上重新分配特征方差，在对应核之间产生大的几何分离；该分离随不可区分度超线性增长，对于2至4个光子，在小可见度下与Hong-Ou-Mandel可见度呈线性关系，在当前量子处理器的源质量下保留约80%的幅度。在实验采样预算下，该分离在对抗性构造的任务上可学习（准确率优势为0.22±0.05），在自然任务上则小一个数量级，由核-任务对齐决定。这些结果调和了现有实验记录，并提供了预实验协议：核几何证明存在干涉特异性学习资源，任务对齐决定给定任务能否访问该资源，两者在投入大量硬件资源前均可计算。
英文摘要
Multi-photon interference is the resource most native to photonic quantum machine learning, yet experiments on photonic reservoirs have reported advantages, null results, and train-only effects. These outcomes cannot be compared: each measures task-dependent accuracy on different tasks and platforms. Here we resolve the question task-independently through the kernel geometry of boson-sampling feature maps. Interference redistributes feature variance across roughly twice as many effective dimensions as distinguishable-particle statistics, generating a large geometric separation between the corresponding kernels. The separation grows superlinearly with indistinguishability, is linear in Hong--Ou--Mandel visibility at small visibility for two to four photons, and retains approximately 80% of its magnitude at the source quality of current quantum processors. Under experimental sampling budgets the separation is learnable on adversarially constructed tasks (accuracy advantage +0.22 plus or minus 0.05) and an order of magnitude smaller on natural tasks, gated by kernel--task alignment. The results reconcile the existing experimental record and supply a pre-experimental protocol: kernel geometry establishes that an interference-specific learning resource exists, and task alignment determines whether a given task can access it; both are computable before committing significant hardware resources.
发表机构
- Indian Institute of Information Technology Dharwad（印度信息技术学院达瓦德分校）
机构由 AI 辅助整理，请以论文原文为准。
