ROSE: Deep Learning exchange-correlation functional from reduced density-matrix representations
physics.comp-ph, physics.chem-ph
Submitted: 2026-10-31
Updated: 2026-10-31
Comments: 15 pages, 7 figures
Code: https://github.com/deepmodeling/deepks-kit
License: http://creativecommons.org/licenses/by/4.0/
The gist: We introduce ROSE, a deep-learning exchange--correlation energy functional built from the occupied-state density matrix.
Terminology
Abstract
We introduce ROSE, a deep-learning exchange--correlation energy functional built from the occupied-state density matrix. On GMTKN55 and on additional external benchmarks considered in this work, ROSE improves over modern neural network functionals trained under matched protocols and is on average more accurate than, or on par with, most hybrid and range-separated hybrid functionals considered here. On the experimental benchmarks considered here it has leading accuracy across hybrids, range separated hybrids, and neural functionals. These results motivate nonlocal density-matrix representations as a route to systematic improvement of learned XC functionals with low computational cost.
Sources
Related papers
- Gradient-Based Inverse Design of Free-Energy Landscapes with Diffusion Models
- Mixture of Polyconvex Neural Potentials for Parametric Hyperelasticity: Towards Foundation Material Models
- Development and large-scale benchmarks of a protein--ligand absolute binding free energy toolkit
- Spin disorder competing with positional symmetry breaking governs the metal-insulator behavior in oxide paramagnets
- Investigation of the Asymptotic Properties of Active Impedance in Large Finite Array Antennas
- Automatic generation of exchange-correlation response kernels