English

Neural-Network Quantum Embedding Solvers for Correlated Materials

Strongly Correlated Electrons 2026-03-25 v2

Abstract

Quantum impurity solvers are the computational bottleneck of quantum embedding approaches to correlated materials, such as dynamical mean-field theory (DMFT). We show that neural networks trained on synthetic, material-agnostic data learn the impurity mapping from hybridization functions and local interactions to Green's functions with quantitative accuracy for both model systems and real materials, providing fast solvers for single- and multi-orbital models. Benchmarks against numerically controlled quantum Monte Carlo show that the method reproduces the Mott transition, multi-orbital phase diagrams of Hubbard-Kanamori models, and the electronic properties of SrVO3_3 and SrMnO3_3. The learned solvers achieve orders-of-magnitude speedup and can initialize controlled calculations, dramatically accelerating DMFT while preserving accuracy.

Keywords

Cite

@article{arxiv.2603.15741,
  title  = {Neural-Network Quantum Embedding Solvers for Correlated Materials},
  author = {Agnes Valenti and Ina Park and Antoine Georges and Andrew J. Millis and Olivier Parcollet},
  journal= {arXiv preprint arXiv:2603.15741},
  year   = {2026}
}
R2 v1 2026-07-01T11:22:58.098Z