用小规模RNN优化大模型，降低量子模拟计算成本。
Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
- 用小RNN训练后复用初始化大RNN，实现自适应优化。
- 计算成本降低，训练波动减少，基态能计算更准确。
- 适合大规模量子多体系统模拟的资源受限场景。
神经网络量子态（NQS）是基于变分原理研究量子多体物理的强大神经网络变分形式，可通过增加参数数量系统性提升精度。本文以循环神经网络（RNN）为例，提出一种自适应优化方法：通过少量计算成本训练小型RNN，并将其结果用于初始化更大规模的RNN，显著降低整体计算开销，同时减少训练波动，提升一维和二维典型模型基态计算的变分质量。该方法为大规模NQS模拟中图形处理器（GPU）资源的高效部署提供了新思路。
原文摘要 · Abstract (English)
Neural-network quantum states (NQS) are powerful neural-network ansätzes that have emerged as promising tools for studying quantum many-body physics through the lens of the variational principle. These architectures are known to be systematically improvable by increasing the number of parameters. Here we demonstrate an Adaptive scheme to optimize NQSs, through the example of recurrent neural networks (RNN), using a fraction of the computation cost while reducing training fluctuations and improving the quality of variational calculations targeting ground states of prototypical models in one- and two-spatial dimensions. This Adaptive technique reduces the computational cost through training small RNNs and reusing them to initialize larger RNNs. This work opens up the possibility for optimizing graphical processing unit (GPU) resources deployed in large-scale NQS simulations.
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。