按年被提到
20192019 · 1 次2026
机器学习与深度学习›科学机器学习·arXiv:1909.08423 · physics.comp-ph

Deep neural network solution of the electronic Schrödinger equation

Jan Hermann, Zeno Schätzle, Frank Noé · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-11-22 · 最近 2020-07-21
2不同的人
2活跃月份
2讨论串
555被引(OpenAlex)
arXiv 摘要(候选层不写导读)

[New and updated results were published in Nature Chemistry, doi:10.1038/s41557-020-0544-y.] The electronic Schrödinger equation describes fundamental properties of molecules and materials, but can only be solved analytically for the hydrogen atom. The numerically exact full configuration-interaction method is exponentially expensive in the number of electrons. Quantum Monte Carlo is a possible way out: it scales well to large molecules, can be parallelized, and its accuracy has, as yet, only been limited by the flexibility of the used wave function ansatz. Here we propose PauliNet, a deep-learning wave function ansatz that achieves nearly exact solutions of the electronic Schrödinger equation. PauliNet has a multireference Hartree-Fock solution built in as a baseline, incorporates the physics of valid wave functions, and is trained using variational quantum Monte Carlo (VMC). PauliNet outperforms comparable state-of-the-art VMC ansatzes for atoms, diatomic molecules and a strongly-correlated hydrogen chain by a margin and is yet computationally efficient. We anticipate that thanks to the favourable scaling with system size, this method may become a new leading method for highly accurate electronic-strucutre calculations on medium-sized molecular systems.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论jhrmnn · 2019-11

“This year, I’ve been working on representing electronic wave functions with neural networks: https://arxiv.org/abs/1909.08423 I come from a physics background, and my impression is that NNs are a cool computational tool that every computational physicist probably should have in their toolbox (at least having a sense of their capability). But so far I have…”

The revolution of machine learning has been exaggerated原评论 ↗
评论currymj · 2020-07

“this is very cool. I was thinking specifically of this and related approaches https://arxiv.org/abs/1909.08423 where they search for the ground state by iteratively using an MCMC sampler and doing SGD. The innovation is a network architecture that takes classic approaches from physics and judiciously replaces parts with flexible NNs. I had not even cons…”

AI in physics: are we facing a scientific revolution?原评论 ↗