aiqbench analysis
This research introduces Langevin Flow Maps, a method that integrates machine learning directly into stochastic Langevin integrators to accelerate molecular dynamics simulations by an order of magnitude. By enabling large-timestep integration while preserving accurate dynamical properties, the approach significantly reduces computational costs for estimating long-timescale ensemble properties and transition paths. The work demonstrates a viable path toward transferable models trained on diverse molecular datasets, bridging the gap between speed and accuracy in physics-informed AI applications.
Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling
arXiv:2610.05998v1 Announce Type: new Abstract: Molecular dynamics simulations proceed by integrating the Langevin equations over many small femtosecond timesteps. This poses a challenge for estimating ensemble properties and transition dynamics that occur on much longer timescales. We introduce Langevin Flow Maps, which extend machine-learned force-fields to additionally learn the stochastic Langevin integrator. We show that Langevin Flow Maps enable large-timestep molecular dynamics and recover accurate dynamical properties of the system, while running an order of magnitude faster than current machine-learned force fields. Further, by training on a diverse molecular dataset, we demonstrate a path towards transferable Langevin Flow Maps.
Abstract:Molecular dynamics simulations proceed by integrating the Langevin equations over many small femtosecond timesteps. This poses a challenge for estimating ensemble properties and transition dynamics that occur on much longer timescales. We introduce Langevin Flow Maps, which extend machine-learned force-fields to additionally learn the stochastic Langevin integrator. We show that Langevin Flow Maps enable large-timestep molecular dynamics and recover accurate dynamical properties of the system, while running an order of magnitude faster than current machine-learned force fields. Further, by training on a diverse molecular dataset, we demonstrate a path towards transferable Langevin Flow Maps.
Machine Learning (cs.LG)
arXiv:2610.05998 [cs.LG]
(or arXiv:2610.05998v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.05998 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 188 words
