Efficient GPU-Accelerated Training of a Neuroevolution Potential with Analytical Gradients
arXiv:2507.00528 · doi:10.1016/j.cpc.2025.109994
Abstract
Machine-learning interatomic potentials (MLIPs) such as neuroevolution potentials (NEP) combine quantum-mechanical accuracy with computational efficiency significantly accelerate atomistic dynamic simulations. Trained by derivative-free optimization, the normal NEP achieves good accuracy, but suffers from inefficiency due to the high-dimensional parameter search. To overcome this problem, we present a gradient-optimized NEP (GNEP) training framework employing explicit analytical gradients and the Adam optimizer. This approach greatly improves training efficiency and convergence speedily while maintaining accuracy and physical interpretability. By applying GNEP to the training of Sb-Te material systems(datasets include crystalline, liquid, and disordered phases), the fitting time has been substantially reduced-often by orders of magnitude-compared to the NEP training framework. The fitted potentials are validated by DFT reference calculations, demonstrating satisfactory agreement in equation of state and radial distribution functions. These results confirm that GNEP retains high predictive accuracy and transferability while considerably improved computational efficiency, making it well-suited for large-scale molecular dynamics simulations.
References in corpus (12)
- Canonical sampling through velocity-rescaling
- VASPKIT: A User-friendly Interface Facilitating High-throughput Computing and Analysis Using VASP Code
- CP2K: An Electronic Structure and Molecular Dynamics Software Package -- Quickstep: Efficient and Accurate Electronic Structure Calculations
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- Moment Tensor Potentials: a class of systematically improvable interatomic potentials
- A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
- Active learning of linearly parametrized interatomic potentials
- GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
- Force and heat current formulas for many-body potentials in molecular dynamics simulation with applications to thermal conductivity calculations
- Phase transitions in inorganic halide perovskites from machine learning potentials
- On the design space between molecular mechanics and machine learning force fields
- ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training