用于设计光子量子实验的多项式神经代理模型
Polynomial neural surrogates for designing photonic quantum experiments
浏览论文内容
中文总结 AI 辅助
本文为PyTheus量子光学模拟器开发了物理启发的多项式神经代理模型，以更少参数实现更高预测精度，并加速GHZ、W和线性簇态的逆向设计，展示了物理知识融入神经代理的高效性。
中文摘要 AI 辅助
物理模拟器可以通过预测实验配置产生的量子态来支持量子实验的发现。当这些模拟器计算成本高昂时，重复调用模拟器可能会限制对产生所需量子态的实验的搜索。在此，我们为PyTheus（一种基于图的量子光学模拟器）开发了一种受物理启发的多项式神经代理模型，用于预测量子态，并将其用于设计量子实验。其多项式激活函数源于图完美匹配与所得态振幅之间的关系。我们分别为四光子、六光子和八光子系统训练了独立的代理模型，并表明它们比标准多层感知器以更少的可训练参数实现了更高的预测精度。然后，我们使用训练好的代理模型对GHZ态、W态和线性簇态进行逆向设计。对于较大的系统，代理模型还使得逆向设计比直接使用PyTheus优化更快。这些结果表明，将底层物理知识融入神经代理模型可以为量子实验设计提供一种高效的方法。
英文摘要
Physics simulators can support the discovery of quantum experiments by predicting the states generated by experimental configurations. When these simulators are computationally expensive, repeated simulator calls can limit the search for experiments that generate a desired quantum state. Here, we develop a physics-inspired polynomial neural surrogate for PyTheus, a graph-based quantum-optics simulator, to predict quantum states and use it to design quantum experiments. Its polynomial activations are motivated by the relation between graph perfect matchings and the resulting state amplitudes. We train separate surrogate models for four-, six-, and eight-photon systems and show that they achieve higher prediction accuracy with fewer trainable parameters than standard multilayer perceptrons. We then use the trained surrogates for inverse design of GHZ, W, and linear-cluster states. For the larger systems, the surrogates also enable faster inverse design than direct optimization with PyTheus. These results suggest that incorporating the underlying physics into neural surrogates can provide an efficient approach to quantum experiment design.
发表机构
- Friedrich Schiller University Jena（耶拿弗里德里希·席勒大学）
机构由 AI 辅助整理，请以论文原文为准。
