From Algebraic Completeness to Orbit Separation: Recursive Separating Invariants for Global Neural Network Potential Energy Surfaces
Abstract
Permutationally invariant polynomials (PIPs) provide a systematically improvable, symmetry-preserving representation for global potential energy surfaces (PESs), but their high computational cost as neural network descriptors limits applications to large molecular systems. Fundamental invariants (FIs), which form an algebraically complete generating set, substantially reduce the number of descriptors and enable neural network PESs for larger systems. However, PES evaluation remains computationally expensive as molecular size and complexity increase. Here, we introduce recursive separating invariants (RSIs), shifting the descriptor design principle from algebraic completeness to orbit separation. RSIs are constructed systematically through correlation order and recursion depth, providing a more computationally efficient representation. Benchmarks on reactive and nonreactive systems demonstrate that RSI-based neural network (RSI-NN) PESs achieve approximately an order-of-magnitude faster evaluation than their FI-NN counterparts, with system-dependent prediction accuracy that is comparable in several cases. These results establish orbit separation as a promising principle for developing efficient symmetry-preserving descriptors for global neural network PESs.
Related
- From ⟨ n ⟩ to n: Separating multi-particle dynamics by intensity cycling
- Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
- Separating hydration propensity from hydrogen bond donation in trifluoromethyl ketone warheads
- Separating perception from reasoning in vision-language models: a model-free render ceiling for crystal structures
- Conformational Dynamics of Phase-Separating Methacrylated Carbohydrates
BibTeX
@misc{hao2026from,
title = {{From Algebraic Completeness to Orbit Separation: Recursive Separating Invariants for Global Neural Network Potential Energy Surfaces}},
author = {Yiping Hao and Jing Lou and Bina Fu and Dong H. Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.21700},
eprint = {2610.21700},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.21700},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - From Algebraic Completeness to Orbit Separation: Recursive Separating Invariants for Global Neural Network Potential Energy Surfaces
AU - Yiping Hao
AU - Jing Lou
AU - Bina Fu
AU - Dong H. Zhang
PY - 2026
DA - 2026/10/15
PB - arXiv
DO - 10.48550/arxiv.2610.21700
UR - https://arxiv.org/abs/2610.21700
AB - Permutationally invariant polynomials (PIPs) provide a systematically improvable, symmetry-preserving representation for global potential energy surfaces (PESs), but their high computational cost as neural network descriptors limits applications to large molecular systems. Fundamental invariants (FIs), which form an algebraically complete generating set, substantially reduce the number of descriptors and enable neural network PESs for larger systems. However, PES evaluation remains computationally expensive as molecular size and complexity increase. Here, we introduce recursive separating invariants (RSIs), shifting the descriptor design principle from algebraic completeness to orbit separation. RSIs are constructed systematically through correlation order and recursion depth, providing a more computationally efficient representation. Benchmarks on reactive and nonreactive systems demonstrate that RSI-based neural network (RSI-NN) PESs achieve approximately an order-of-magnitude faster evaluation than their FI-NN counterparts, with system-dependent prediction accuracy that is comparable in several cases. These results establish orbit separation as a promising principle for developing efficient symmetry-preserving descriptors for global neural network PESs.
ER -