Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces
2026-02-16 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed DMTS-NC, a new way to speed up molecular simulations by using a mix of accurate and simplified models with non-conservative forces. Their method builds on earlier work by combining these models through a special algorithm, ensuring important physics rules are still followed. This approach makes simulations run faster and more stable without extra tuning, and it works with any neural network potential. Overall, their method achieves better performance compared to previous techniques while keeping accuracy.
Molecular dynamicsNeural network potentialNon-conservative forcesRESPA algorithmDistillationEquivarianceForce fieldsMulti-time-step integrationAtomistic simulation
Authors
Nicolaï Gouraud, Côme Cattin, Thomas Plé, Olivier Adjoua, Louis Lagardère, Jean-Philip Piquemal
Abstract
Following our previous work (J. Phys. Chem. Lett., 2026, 17, 5, 1288-1295), we propose the DMTS-NC approach, a distilled multi-time-step (DMTS) strategy using non conservative (NC) forces to further accelerate atomistic molecular dynamics simulations using foundation neural network models. There, a dual-level reversible reference system propagator algorithm (RESPA) formalism couples a target accurate conservative potential to a simplified distilled representation optimized for the production of non-conservative forces. Despite being non-conservative, the distilled architecture is designed to enforce key physical priors, such as equivariance under rotation and cancellation of atomic force components. These choices facilitate the distillation process and therefore improve drastically the robustness of simulation, significantly limiting the "holes" in the simpler potential, thus achieving excellent agreement with the forces data. Overall, the DMTS-NC scheme is found to be more stable and efficient than its conservative counterpart with additional speedups reaching 15-30% over DMTS. Requiring no finetuning steps, it is easier to implement and can be pushed to the limit of the systems physical resonances to maintain accuracy while providing maximum efficiency. As for DMTS, DMTS-NC is applicable to any neural network potential.