Assessments of machine-learned (ML) potentials are an important aspect of the rapid development of this field. We recently reported an assessment of the linear-regression permutationally invariant polynomial (PIP) method for ethanol, using the widely used (revised) MD17 dataset. We demonstrated that the PIP approach outperformed numerous other methods, e.g., ANI, PhysNet, sGDML, p-KRR, with respect to precision and notably with respect to speed [Houston etal., J.Chem.Phys. 2022, 156, 044120.]. Here we extend this assessment to the 21-atom aspirin molecule, using the rMD17 dataset. Both energies and forces are used for training and the precision of several PIPs is examined for both. Normal mode frequencies, the methyl torsional potential, and 1d vibrational energies for an OH stretch are presented. Overall, we show that the PIPs approach outperforms other ML methods, including sGDML, ANI, GAP, PhysNet, and ACE, as reported by Kov\'acs etal. in J.Chem.TheoryComput. 2021, 17, 7696-7711.
@article{arxiv.2401.09316,
title = {No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials},
author = {Paul L. Houston and Chen Qu and Qi Yu and Priyanka Pandey and Riccardo Conte and Apurba Nandi and Joel M. Bowman},
journal= {arXiv preprint arXiv:2401.09316},
year = {2024}
}