用单一神经网络预测电子系统基态波函数，跨参数泛化能力强。
Large Electron Model: A Universal Ground State Predictor
- 采用费米集架构构建通用费米子波函数表示，条件化于哈密顿量参数和粒子数。
- 单个模型在二维谐振势中准确预测50个电子的基态波函数与能量。
- 适用于强关联电子系统研究，适合材料发现与量子多体问题求解者。
我们提出大型电子模型（Large Electron Model），一个单一神经网络模型，可在整个哈密顿量参数空间内生成相互作用电子的变分波函数。该模型采用费米集架构，一种通用的多体费米子波函数表示，进一步以哈密顿量参数和粒子数为条件。对于二维谐振势中的相互作用电子系统，单个训练好的模型可准确预测基态波函数，并在未见过的耦合强度和粒子数区间实现泛化，生成精确的实空间电荷密度与基态能量，即使达到50个粒子。结果建立了基于变分原理的奠基性模型方法，能精确处理超出密度泛函理论能力的强电子关联问题。
原文摘要 · Abstract (English)
We introduce Large Electron Model, a single neural network model that produces variational wavefunctions of interacting electrons over the entire Hamiltonian parameter manifold. Our model employs the Fermi Sets architecture, a universal representation of many-body fermionic wavefunctions, which is further conditioned on Hamiltonian parameter and particle number. For interacting electrons in a two-dimensional harmonic potential, a single trained model accurately predicts the ground state wavefunction while generalizing across unseen coupling strengths and particle-number sectors, producing both accurate real-space charge densities and ground state energies, even up to $50$ particles. Our results establish a foundation model method for material discovery that is grounded in the variational principle, while accurately treating strong electron correlation beyond the capacity of density functional theory.
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。