Complete Neural Electronic Initialization Accelerates Materials DFT

This paper introduces a complete machine learning framework for accelerating plane-wave density functional theory calculations in materials using the projector augmented wave formalism. The authors formalize seven criteria that a Complete Neural Electronic Initializer must satisfy for practical end-to-end PAW DFT acceleration. The analysis of prior work reveals two missing structure-dependent components: augmentation occupancies and spin initialization, which are essential for achieving complete neural initialization in DFT computations.