RS-CIDER: A non-local machine learning model for approximating screened hybrid functionals

Abstract

Screened hybrid functionals such as HSE06 improve the description of band gaps, charge localization, and redox energetics relative to semilocal approximations, but their explicit Hartree-Fock exchange term is computationally costly for large, periodic systems, especially in plane-wave basis set calculations. Here we present RS-CIDER, a machine-learned non-local exchange functional that approximates the short-range Hartree-Fock exchange term in HSE06 by explicitly fitting both ground-state energies and single-particle energy levels. RS-CIDER combines scale-invariant semilocal and non-local density descriptors and can be evaluated self-consistently without explicitly applying the short-range Hartree-Fock exchange operator. RS-CIDER shows close agreement with HSE06 for molecular reaction energies and solid-state band gaps. Further tests across distinct materials show agreement between RS-CIDER and HSE06 for local magnetism, Cu-O phase competition, polaron localization, and neutral-defect energetics. For an Fe olivine, chemistry-specific fine-tuning recovers the HSE06 Li intercalation voltage. A timing benchmark shows that RS-CIDER reduces the measured per-SCF-step wall time by more than an order of magnitude relative to HSE06. Together, these molecular and solid-state results establish RS-CIDER as an efficient self-consistent machine-learned surrogate for HSE06.

What Does a Semilocal Machine-Learning Correction Actually Learn? Size-Dependent Errors across Four Parent Functionals
Abhishek Bhattacharjee, Kishan Kumar Mohanta, Subrata Jana +1
arXiv29 Sep 2026PreprintarXiv licenceFull textPhysical chemistry Condensed matterarXiv
Discovery of germanium-based hybrid perovskites with high photovoltaic performance with machine-learning
Carrie Song, R. X. Lian, H. Zhang +1
RSC advances22 Oct 2026Peer-reviewedCC BY-NCFull textMaterials & polymersEurope PMCPMC
Composition-Dependent Self-Diffusion Coefficients in Liquid Mixtures from Hybrid Machine Learning
Jens Wagner, Thomas Specht, Hans Hasse +1
arXiv21 Sep 2026PreprintCC BY 4.0Full textPhysical chemistryarXiv
Functional Tree Forest: A Hybrid Bagging-Boosting Ensemble Machine Learning Approach for Battery Fault Diagnosis in Electric Vehicles
Ibrahim Kubilay, Derya Birant
Batteries26 Oct 2026Peer-reviewedCC BY 4.0Electrochemistry & energyCrossref
Accessible hybrid DFT-quality NMR crystallography via gas-phase machine learning interatomic potentials
Shubha S. Gunaga, Robert W. Schurko, Sean T. Holmes +1
Chemical Science8 Sep 2026Peer-reviewedCC BY-NC 3.0Full text2 citedPhysical chemistryPMC

Cite

BibTeX RIS

BibTeX

@misc{jin2026rscider,
  title = {{RS-CIDER: A non-local machine learning model for approximating screened hybrid functionals}},
  author = {Zhuotao Jin and Mohamed S. Abdallah and Boris Kozinsky and Kyle Bystrom},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.13139},
  eprint = {2609.13139},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.13139},
}

RIS

TY  - UNPB
TI  - RS-CIDER: A non-local machine learning model for approximating screened hybrid functionals
AU  - Zhuotao Jin
AU  - Mohamed S. Abdallah
AU  - Boris Kozinsky
AU  - Kyle Bystrom
PY  - 2026
DA  - 2026/09/11
PB  - arXiv
DO  - 10.48550/arxiv.2609.13139
UR  - https://arxiv.org/abs/2609.13139
AB  - Screened hybrid functionals such as HSE06 improve the description of band gaps, charge localization, and redox energetics relative to semilocal approximations, but their explicit Hartree-Fock exchange term is computationally costly for large, periodic systems, especially in plane-wave basis set calculations. Here we present RS-CIDER, a machine-learned non-local exchange functional that approximates the short-range Hartree-Fock exchange term in HSE06 by explicitly fitting both ground-state energies and single-particle energy levels. RS-CIDER combines scale-invariant semilocal and non-local density descriptors and can be evaluated self-consistently without explicitly applying the short-range Hartree-Fock exchange operator. RS-CIDER shows close agreement with HSE06 for molecular reaction energies and solid-state band gaps. Further tests across distinct materials show agreement between RS-CIDER and HSE06 for local magnetism, Cu-O phase competition, polaron localization, and neutral-defect energetics. For an Fe olivine, chemistry-specific fine-tuning recovers the HSE06 Li intercalation voltage. A timing benchmark shows that RS-CIDER reduces the measured per-SCF-step wall time by more than an order of magnitude relative to HSE06. Together, these molecular and solid-state results establish RS-CIDER as an efficient self-consistent machine-learned surrogate for HSE06.
ER  -

Abstract

Related

Cite