Many-body perturbation theory with hybrid density functional theory starting points accelerated by adaptively compressed exchange

TL;DR

This paper introduces an ACE-based acceleration method for many-body perturbation theory calculations starting from hybrid density functional theory, significantly reducing computational costs while maintaining accuracy.

Contribution

The authors develop an ACE-accelerated approach for MBPT calculations that avoids explicit empty state computations, enabling faster and scalable G0W0 and BSE computations from hybrid DFT starting points.

Findings

Achieves substantial computational savings with controllable errors.

Demonstrates robustness across CPU and GPU implementations.

Facilitates exploration of hybrid functionals for improved MBPT accuracy.

Abstract

We report on the use of the adaptively compressed exchange (ACE) operator to accelerate many-body perturbation theory (MBPT) calculations, including G$_0$W$_0$ and the Bethe Salpeter equation (BSE), for hybrid density functional theory starting points. We show that by approximating the exact exchange operator with the low-rank ACE operator, substantial computational savings can be achieved with systematically controllable errors in the quasiparticle energies computed with full-frequency G$_0$W$_0$ and the optical absorption spectra and vertical excitation energies computed by solving the BSE within density matrix perturbation theory. Our implementation makes use of the ACE-accelerated electronic Hamiltonian to carry out both G$_0$W$_0$ and BSE without explicitly computing empty states. We show the robustness of the approach and present the computational gains obtained on both the central processing unit and graphics processing unit nodes. Our work will facilitate the exploration and evaluation of fine-tuned hybrid starting points aimed at enhancing the accuracy of MBPT calculations without involving computationally demanding self-consistency in Hedin's equations.