Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory

TL;DR

This paper introduces a neural network-based method to improve exchange-correlation functionals in Density Functional Theory by estimating uncertainty, leading to significant accuracy improvements over existing methods in benchmark tests.

Contribution

The paper proposes a novel residual functional that predicts both mean and variance of the XC functional, enhancing DFT accuracy especially in systematic error cases.

Findings

Outperforms state-of-the-art methods in benchmark tests

Achieves 62% and 37% RMSE improvements over B3LYP and DM21

Significantly reduces systematic errors in XC approximations

Abstract

Density Functional Theory (DFT) stands as a widely used and efficient approach for addressing the many-electron Schr\"odinger equation across various domains such as physics, chemistry, and biology. However, a core challenge that persists over the long term pertains to refining the exchange-correlation (XC) approximation. This approximation significantly influences the triumphs and shortcomings observed in DFT applications. Nonetheless, a prevalent issue among XC approximations is the presence of systematic errors, stemming from deviations from the mathematical properties of the exact XC functional. For example, although both B3LYP and DM21 (DeepMind 21) exhibit improvements over previous benchmarks, there is still potential for further refinement. In this paper, we propose a strategy for enhancing XC approximations by estimating the neural uncertainty of the XC functional, named Residual XC-Uncertain Functional. Specifically, our approach involves training a neural network to predict both the mean and variance of the XC functional, treating it as a Gaussian distribution. To ensure stability in each sampling point, we construct the mean by combining traditional XC approximations with our neural predictions, mitigating the risk of divergence or vanishing values. It is crucial to highlight that our methodology excels particularly in cases where systematic errors are pronounced. Empirical outcomes from three benchmark tests substantiate the superiority of our approach over existing state-of-the-art methods. Our approach not only surpasses related techniques but also significantly outperforms both the popular B3LYP and the recent DM21 methods, achieving average RMSE improvements of 62\% and 37\%, respectively, across the three benchmarks: W4-17, G21EA, and G21IP.