用神经网络自动选量子测量，效率远超随机选择。
Sequence-Model-Guided Measurement Selection for Quantum State Learning
- 用序列模型神经网络动态选择最优测量
- 在多种任务中均优于随机测量，尤其对拓扑系统推荐边界测量
- 发现边界与体性关联，暗示模型自主学习物理规律
从实验数据表征量子系统是量子科学与技术的核心问题。但应选择哪些测量来收集数据？对于小系统可求出最优测量，但系统规模增大后优化变得不可行。为此，我们提出一种基于序列模型架构的深度神经网络，以数据驱动、自适应方式搜索高效测量方案。该模型适用于线性与非线性量子态性质预测、状态聚类及态层析等多种任务。所有任务中，神经网络选出的测量均显著优于均匀随机选择。令人惊讶的是，针对拓扑量子系统，即使任务是预测体性质，模型也倾向于推荐边界测量。这一行为暗示神经网络可能在未提供任何量子物理先验知识的情况下，自主发现了边界与体之间的关联。
原文摘要 · Abstract (English)
Characterization of quantum systems from experimental data is a central problem in quantum science and technology. But which measurements should be used to gather data in the first place? While optimal measurement choices can be worked out for small quantum systems, the optimization becomes intractable as the system size grows large. To address this problem, we introduce a deep neural network with a sequence model architecture that searches for efficient measurement choices in a data-driven, adaptive manner. The model can be applied to a variety of tasks, including the prediction of linear and nonlinear properties of quantum states, as well as state clustering and state tomography tasks. In all these tasks, we find that the measurement choices identified by our neural network consistently outperform the uniformly random choice. Intriguingly, for topological quantum systems, our model tends to recommend measurements at the system's boundaries, even when the task is to predict bulk properties. This behavior suggests that the neural network may have independently discovered a connection between boundaries and bulk, without having been provided any built-in knowledge of quantum physics.
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。