arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05345physics.chem-ph
收藏

端到端可微学习单个功能用于DFT和线性响应TDDFT

End-to-End Differentiable Learning of a Single Functional for DFT and Linear-Response TDDFT

College of Chemistry and Molecular Engineering, Peking University(北京大学化学与分子工程学院)

Xiaoyu Zhang

AI总结:

本文提出端到端可微学习方法,通过Kohn-Sham DFT和Adiabatic LR-TDDFT的目标优化单个深度学习能量功能,结合自洽场方程和Casida本征值问题进行梯度优化。

摘要:

密度泛函理论(DFT)和线性响应时间依赖密度泛函理论(LR-TDDFT)依赖于交换关联(xc)近似,不仅提供能量,还提供其泛函导数,进入自洽势能和响应核。本文提出端到端可微工作流程,通过Kohn-Sham DFT和Adiabatic LR-TDDFT的目标优化单个深度学习能量泛函。为实现高效且可微的训练,我们开发了基于JAX的双组分量子化学框架(IQC),其中学习的泛函通过自动微分提供自洽势能和线性响应核。此构造允许通过自洽场(SCF)固定点方程和Casida本征值问题进行基于梯度的优化。我们学习了小分子激发能的交换关联泛函,同时结合单电子自相互作用抵消作为惩罚项,并评估其在分子测试案例中的可能转移。

英文摘要:

Density functional theory (DFT) and linear-response time-dependent density functional theory (LR-TDDFT) rely on an exchange-correlation (xc) approximation that provides not only energy but also its functional derivatives that enter the self-consistent potential and the response kernel. Here, we present an end-to-end differentiable workflow to optimize a single deep-learned energy functional using targets from both Kohn-Sham DFT and adiabatic LR-TDDFT. To enable this training in a computationally efficient and differentiable manner, we developed a JAX-based two-component quantum chemistry package (IQC), in which the learned functional provides a self-consistent potential and linear-response kernel via automatic differentiation. This construction permits gradient-based optimization through both the self-consistent-field (SCF) fixed-point equations and the Casida eigenvalue problem. We learn an exchange-correlation functional on excitation energies and ground-state properties (noncovalent interactions, thermochemistry, bond dissociation, ionization potentials, electron affinities, isomerization energies, and reaction barriers) while incorporating one-electron self-interaction cancelation as penalty terms, and we assess its possible transfer to molecular test cases.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑