Data-Driven Complete Basis Set Limit Estimates from a Minimal Auxiliary Basis
- 1Institut für Chemie, Universität Kassel, Heinrich-Plett-Straße 40, Kassel 34132, Germany
- 2Center for Interdisciplinary Nanostructure Science and Technology (CINSaT), Heinrich-Plett-Straße 40, Kassel 34132, Germany
Abstract
Quantum chemistry calculations are often performed using atom-centered basis sets, which are chosen to balance accuracy and cost. While they are systematically improvable, the total energy converges slowly with basis set size toward the complete basis set (CBS) limit. Common extrapolation methods require several intermediate-quality calculations to afford an estimate of the CBS energy. We propose a minimal complementary auxiliary basis set (CABS) baseline to estimate the CBS energy from a single quantum chemistry calculation in a minimal basis set via kernel ridge regression (KRR), which is more efficient than both direct and Δ-machine learning and 40× faster than triple-ζ single-point calculations. The spatial and alchemical gradients from minimal basis and minimal CABS are more accurate than double-ζ (DZ) calculations. We show that KRR on standard molecular representations can be improved by approximating atom-wise local kernels using Chebyshev polynomials, which allows us to train KRR models 10×–50× times faster on moderate compute resources, thereby enabling a data-driven approach toward the mean-field CBS, combining physical baselines capturing leading-order effects with data-efficient machine learning models.
Related
- Lepton-Number Violation in Higgs Effective Field Theory: Complete Operator Basis and Type-II Seesaw Matching
- Parity-violating scalar-tensor theory revisited: complete basis up to d=4 and Hamiltonian analysis
- When can local unitaries generate a complete orthogonal basis?
- Finite basis Kolmogorov-Arnold networks: Domain decomposition for data-driven and physics-informed problems
- Algebraic criteria for complete relaxation in autonomous and periodically driven open quantum systems
BibTeX
@article{grimblat2026datadriven,
title = {{Data-Driven Complete Basis Set Limit Estimates from a Minimal Auxiliary Basis}},
author = {Nicolas Grimblat and Gabriel Klassen and Guido Falk von Rudorff},
journal = {Journal of Chemical Theory and Computation},
year = {2026},
month = oct,
doi = {10.1021/acs.jctc.6c01004},
url = {https://doi.org/10.1021/acs.jctc.6c01004},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Data-Driven Complete Basis Set Limit Estimates from a Minimal Auxiliary Basis
AU - Nicolas Grimblat
AU - Gabriel Klassen
AU - Guido Falk von Rudorff
PY - 2026
DA - 2026/10/19
JO - Journal of Chemical Theory and Computation
DO - 10.1021/acs.jctc.6c01004
UR - https://doi.org/10.1021/acs.jctc.6c01004
AB - Quantum chemistry calculations are often performed using atom-centered basis sets, which are chosen to balance accuracy and cost. While they are systematically improvable, the total energy converges slowly with basis set size toward the complete basis set (CBS) limit. Common extrapolation methods require several intermediate-quality calculations to afford an estimate of the CBS energy. We propose a minimal complementary auxiliary basis set (CABS) baseline to estimate the CBS energy from a single quantum chemistry calculation in a minimal basis set via kernel ridge regression (KRR), which is more efficient than both direct and Δ-machine learning and 40× faster than triple-ζ single-point calculations. The spatial and alchemical gradients from minimal basis and minimal CABS are more accurate than double-ζ (DZ) calculations. We show that KRR on standard molecular representations can be improved by approximating atom-wise local kernels using Chebyshev polynomials, which allows us to train KRR models 10×–50× times faster on moderate compute resources, thereby enabling a data-driven approach toward the mean-field CBS, combining physical baselines capturing leading-order effects with data-efficient machine learning models.
SN - 1549-9618
SN - 1549-9626
ER -