Deep neural networks have become a highly accurate and powerful wavefunction ansatz in combination with variational Monte Carlo methods for solving the electronic Schr\"odinger equation. However, despite their success and favorable scaling, these methods are still computationally too costly for wide adoption. A significant obstacle is the requirement to optimize the wavefunction from scratch for each new system, thus requiring long optimization. In this work, we propose a novel neural network ansatz, which effectively maps uncorrelated, computationally cheap Hartree-Fock orbitals, to correlated, high-accuracy neural network orbitals. This ansatz is inherently capable of learning a single wavefunction across multiple compounds and geometries, as we demonstrate by successfully transferring a wavefunction model pre-trained on smaller fragments to larger compounds. Furthermore, we provide ample experimental evidence to support the idea that extensive pre-training of a such a generalized wavefunction model across different compounds and geometries could lead to a foundation wavefunction model. Such a model could yield high-accuracy ab-initio energies using only minimal computational effort for fine-tuning and evaluation of observables.

翻译：深度神经网络结合变分蒙特卡罗方法已成为求解电子薛定谔方程的高度精确且功能强大的波函数拟设。然而，尽管这些方法取得了成功且具有可扩展性优势，其计算成本仍然过高，难以广泛应用。一个主要障碍在于，每个新系统都需要从头开始优化波函数，从而耗费大量优化时间。在本研究中，我们提出了一种新型神经网络拟设，能够有效地将无关联、计算成本低廉的哈特里-福克轨道映射为关联性强、高精度的神经网络轨道。该拟设本身具备跨多种化合物和几何构型学习单一波函数的能力，我们通过成功将预训练于较小片段上的波函数模型迁移至更大化合物这一实验进行了验证。此外，我们提供了充分的实验证据，支持以下观点：在多种化合物和几何构型上对此类泛化波函数模型进行大规模预训练，有望构建出一个基础波函数模型。该模型仅需极少的计算资源进行微调和可观测量的评估，即可获得高精度的从头算能量。