Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
This paper introduces parameter-reduced magnetic Moment Tensor Potentials (mMTPs) by applying low-rank matrix and tensor factorizations. The compressed potentials achieve parameter reduction factors of 1.5-3 while maintaining predictive accuracy for magnetic, structural, and vibrational properties. Molecular dynamics simulations of Fe-Al and CrN systems using the compressed mMTPs yield results consistent with the uncompressed model, DFT, and experimental data.
Magnetic ML potentials are compressed by up to 3x with no loss in predictive accuracy, enabling faster simulations.
We propose a parameter-reduced version of magnetic Moment Tensor Potential (mMTP) based on various matrix and tensor decompositions. The resulting compressed magnetic machine-learning potential reduces the number of parameters by a factor of approximately 1.5-3 without compromising predictive performance on the validation set. We evaluate the performance of the compressed potentials for magnetic, structural, and vibrational properties, as well as in molecular dynamics simulations of Fe-Al and CrN systems. We demonstrate that the simulation results obtained with the compressed mMTP are numerically consistent with those of the original uncompressed model and are in agreement with density functional theory calculations and experimental data.