Ma He, Narayanaswamy Arunachalam, Riley Patrick, Li Li
Google Research, Mountain View, CA 94043, USA.
Relay Therapeutics, 399 Binney Street, 2nd Floor, Cambridge, MA 02139, USA.
Sci Adv. 2022 Sep 9;8(36):eabq0279. doi: 10.1126/sciadv.abq0279.
Systematic development of accurate density functionals has been a decades-long challenge for scientists. Despite emerging applications of machine learning (ML) in approximating functionals, the resulting ML functionals usually contain more than tens of thousands of parameters, leading to a huge gap in the formulation with the conventional human-designed symbolic functionals. We propose a new framework, Symbolic Functional Evolutionary Search (SyFES), that automatically constructs accurate functionals in the symbolic form, which is more explainable to humans, cheaper to evaluate, and easier to integrate to existing codes than other ML functionals. We first show that, without prior knowledge, SyFES reconstructed a known functional from scratch. We then demonstrate that evolving from an existing functional ωB97M-V, SyFES found a new functional, GAS22 (Google Accelerated Science 22), that performs better for most of the molecular types in the test set of Main Group Chemistry Database (MGCDB84). Our framework opens a new direction in leveraging computing power for the systematic development of symbolic density functionals.
几十年来，系统地开发精确的密度泛函一直是科学家们面临的挑战。尽管机器学习（ML）在近似泛函方面有新的应用，但由此产生的ML泛函通常包含数万个参数，这导致其在公式化方面与传统的人工设计符号泛函存在巨大差距。我们提出了一个新的框架，即符号泛函进化搜索（SyFES），它能以符号形式自动构建精确的泛函，这种形式对人类来说更具可解释性，评估成本更低，并且比其他ML泛函更易于集成到现有代码中。我们首先表明，在没有先验知识的情况下，SyFES从头开始重建了一个已知的泛函。然后我们证明，从现有的泛函ωB97M-V进化而来，SyFES找到了一个新的泛函GAS22（谷歌加速科学22），它在主族化学数据库（MGCDB84）测试集中的大多数分子类型上表现更好。我们的框架为利用计算能力系统地开发符号密度泛函开辟了一个新方向。
