通过缓慢调优神经量子态，用权重空间变化检测量子相变。
Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space
- 在相图上逐步训练神经量子态，使权重间产生强关联。
- 在伊辛模型和J1-J2自旋模型中，相变对应权重空间的明显结构变化。
- 适合研究机器学习与量子物理交叉的学者，提升模型可解释性。
神经量子态（NQS）利用深度学习近似量子波函数，虽精度高，但其如何编码物理信息仍不清晰。本文提出绝热微调方法，在相图上训练NQS，使不同模型间的权重呈现强相关性。这种权重空间的相关性使得仅通过分析训练后的网络权重即可检测量子系统的相变。我们在横向场伊辛模型和J1-J2海森堡模型上验证该方法，发现相变在权重空间中表现为显著的结构特征。结果建立了物理相变与神经网络参数几何之间的联系，为机器学习在物理中的可解释性开辟新方向。
原文摘要 · Abstract (English)
Neural quantum states (NQS) have emerged as a powerful tool for approximating quantum wavefunctions using deep learning. While these models achieve remarkable accuracy, understanding how they encode physical information remains an open challenge. In this work, we introduce adiabatic fine-tuning, a scheme that trains NQS across a phase diagram, leading to strongly correlated weight representations across different models. This correlation in weight space enables the detection of phase transitions in quantum systems by analyzing the trained network weights alone. We validate our approach on the transverse field Ising model and the J1-J2 Heisenberg model, demonstrating that phase transitions manifest as distinct structures in weight space. Our results establish a connection between physical phase transitions and the geometry of neural network parameters, opening new directions for the interpretability of machine learning models in 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。