arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.03327cond-mat.softcond-mat.stat-mech
收藏

神经密度泛函:局部学习与对关联匹配

Neural density functionals: Local learning and pair-correlation matching

Florian Sammüller, Matthias Schmidt

AI总结:

本研究证明体相对关联匹配是基于局部学习的神经密度泛函的高效正则化项,主张采用局部单体学习实现Mermin-Evans密度泛函映射的灵活建模,可获得超越训练盒限制的精准神经自由能泛函。

摘要:

近期Dijkman等人(arXiv:2403.15007)提出通过体相对关联匹配训练经典神经密度泛函。我们证明该方法是基于非均匀单体直接关联局部学习的神经泛函的高效正则化项[Sammüller等人,Proc. Natl. Acad. Sci. 120, e2312484120 (2023), 10.1073/pnas.2312484120]。Dijkman等人展示了全局神经自由能泛函的对关联匹配,而我们主张采用局部单体学习,以对完整的Mermin-Evans密度泛函映射进行灵活的神经建模。利用空间局部化可获得包括卷积神经网络在内的精准神经自由能泛函,其性能可超越训练盒的限制。

英文摘要:

Recently Dijkman et al. (arXiv:2403.15007) proposed training classical neural density functionals via bulk pair-correlation matching. We show their method to be an efficient regularizer for neural functionals based on local learning of inhomogeneous one-body direct correlations [Sammüller et al., Proc. Natl. Acad. Sci. 120, e2312484120 (2023), 10.1073/pnas.2312484120]. While Dijkman et al. demonstrated pair-correlation matching of a global neural free energy functional, we argue in favor of local one-body learning for flexible neural modelling of the full Mermin-Evans density functional map. Using spatial localization gives access to accurate neural free energy functionals, including convolutional neural networks, that transcend the training box.

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。

↑