用可解释的生成模型高效采样量子化学关键构型，大幅降低计算成本。
Configuration Interaction Guided Sampling with Interpretable Restricted Boltzmann Machine
- 用受限玻尔兹曼机结合禁用列表策略，智能筛选重要电子构型。
- 仅用全组态相互作用的万分之一构型，达到99.99%相关能精度。
- 模型学习到类似径向分布函数的电子分布模式，具备可解释性。
我们提出一种基于受限玻尔兹曼机（RBM）的数据驱动方法，用于在构型空间求解薛定谔方程。传统组态相互作用（CI）方法将波函数表示为斯莱特行列式的线性组合，但随着构型数的阶乘增长，计算成本急剧上升。本方法通过引入禁用列表策略，扩展了生成模型如RBM的应用，能够高效识别并采样最具贡献的行列式，从而加速收敛并显著降低计算开销。该方法在使用比全组态相互作用少四个数量级的行列式时，实现了高达99.99%的相关能；相较于先前最优方法，行列式数量减少达两个数量级。此外，分析表明RBM通过捕捉与分子成键相关的径向分布函数（RDFs）模式，学习到了电子在分子轨道上的分布规律，揭示了其学习结果的可解释性，展示了机器学习在可解释量子化学中的潜力。
原文摘要 · Abstract (English)
We propose a data-driven approach using a Restricted Boltzmann Machine (RBM) to solve the Schrödinger equation in configuration space. Traditional Configuration Interaction (CI) methods construct the wavefunction as a linear combination of Slater determinants, but this becomes computationally expensive due to the factorial growth in the number of configurations. Our approach extends the use of a generative model such as the RBM by incorporating a taboo list strategy to enhance efficiency and convergence. The RBM is used to efficiently identify and sample the most significant determinants, thus accelerating convergence and substantially reducing computational cost. This method achieves up to 99.99% of the correlation energy while using up to four orders of magnitude fewer determinants compared to full CI calculations and up to two orders of magnitude fewer than previous state of the art methods. Beyond efficiency, our analysis reveals that the RBM learns electron distributions over molecular orbitals by capturing quantum patterns that resemble Radial Distribution Functions (RDFs) linked to molecular bonding. This suggests that the learned pattern is interpretable, highlighting the potential of machine learning for explainable quantum chemistry
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。