Semiempirical Quantum Chemistry in the Age of ab initio Data and Differentiable Programming: II. Parameter Optimization
- 1Department of Chemistry and The PULSE Institute
- 2Stanford University
- 3SLAC National Accelerator Laboratory
Abstract
Semiempirical quantum chemistry (SQC) represents an invaluable asset in the toolbox of molecular and materials modeling. Thanks to their explicit quantum-mechanical treatment of electrons, they allow to capture an array of local and non-local interaction mechanisms and offers access to electronic structure properties, which can be of crucial importance in order to better understand and design molecular systems and materials. In a previous publication, we presented our recent advances within the PySEQM package, enabling rapid gradient evaluations for SQC parameters and thus developing an efficient and reliable back-end for SQC parametrizations. In this work, we detail our implementation of this parametrization procedure, SQCFit, and its features. Offering a high degree of automation, SQCFit implements a suite of tailor-made tools for the optimization of SQC parameters. Specifically, we present local versus global parametrization schemes, the use of train-validation splits and early stopping to avoid overfitting, and advanced scoring/loss functions including appropriately standardized quantitative error measures as well as more qualitative measures such as the performance in ranking candidate systems according to a given molecular property. Based on a set of test applications, we highlight how SQCFit allows to obtain performant parametrizations tailor-made for the modern use cases of SQC.
Related
- Semiempirical Quantum Chemistry in the Age of ab initio Data and Differentiable Programming: III. Differentiable Complete Active Space Configuration Interaction
- Bidirectional Refractive-Index Programming via Three-Stage Sequential Thiol-Click Chemistry for High-Performance Holographic Recording
- Measurement-Efficient Differentiable Quantum Architecture Search for Combinatorial Optimization
- Warp-Geo: Differentiable Geometry Representation for Dynamic-Boundary Simulation and Shape Optimization
- A Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization
BibTeX
@misc{stohr2026semiempirical,
title = {{Semiempirical Quantum Chemistry in the Age of ab initio Data and Differentiable Programming: II. Parameter Optimization}},
author = {Martin Stöhr and Todd J. Martínez},
howpublished = {ChemRxiv},
year = {2026},
month = oct,
doi = {10.26434/chemrxiv.15010354/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010354/v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Semiempirical Quantum Chemistry in the Age of ab initio Data and Differentiable Programming: II. Parameter Optimization
AU - Martin Stöhr
AU - Todd J. Martínez
PY - 2026
DA - 2026/10/13
PB - ChemRxiv
DO - 10.26434/chemrxiv.15010354/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010354/v1
AB - Semiempirical quantum chemistry (SQC) represents an invaluable asset in the toolbox of molecular and materials modeling. Thanks to their explicit quantum-mechanical treatment of electrons, they allow to capture an array of local and non-local interaction mechanisms and offers access to electronic structure properties, which can be of crucial importance in order to better understand and design molecular systems and materials. In a previous publication, we presented our recent advances within the PySEQM package, enabling rapid gradient evaluations for SQC parameters and thus developing an efficient and reliable back-end for SQC parametrizations. In this work, we detail our implementation of this parametrization procedure, SQCFit, and its features. Offering a high degree of automation, SQCFit implements a suite of tailor-made tools for the optimization of SQC parameters. Specifically, we present local versus global parametrization schemes, the use of train-validation splits and early stopping to avoid overfitting, and advanced scoring/loss functions including appropriately standardized quantitative error measures as well as more qualitative measures such as the performance in ranking candidate systems according to a given molecular property. Based on a set of test applications, we highlight how SQCFit allows to obtain performant parametrizations tailor-made for the modern use cases of SQC.
ER -