Learning mappings between equilibrium states of liquid systems using normalizing flows
Open Access
- 8 May 2025
- journal article
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 162 (18)
Abstract
Generative models and, in particular, normalizing flows are a promising tool in statistical mechanics to address the sampling problem in condensed-matter systems. In this work, we investigate the potential of normalizing flows to learn a transformation to map different liquid systems into each other while allowing at the same time to obtain an unbiased equilibrium distribution. We apply this methodology to the mapping of a small system of fully repulsive disks modeled via the Weeks–Chandler–Andersen potential into a Lennard-Jones system in the liquid phase at different coordinates in the phase diagram. We obtain an improvement in the relative effective sample size of the generated distribution up to a factor of six compared to direct reweighting. We show that this factor can have a strong dependency on the thermodynamic parameters of the source and target system.Keywords
All Related Versions
Funding Information
- Austrian Science Fund (10.55776/F81)
This publication has 38 references indexed in Scilit:
- Active Learning of Boltzmann Samplers and Potential Energies with Quantum Mechanical AccuracyJournal of Chemical Theory and Computation, 2024
- Coarse-Grained Molecular Dynamics with Normalizing FlowsJournal of Chemical Theory and Computation, 2024
- Sampling thermodynamic ensembles of molecular systems with generative neural networks: Will integrating physics-based models close the generalization gap?Current Opinion in Solid State and Materials Science, 2024
- Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular DynamicsJournal of Chemical Theory and Computation, 2023
- Uniform-in-phase-space data selection with iterative normalizing flowsData-Centric Engineering, 2023
- Flow-Matching: Efficient Coarse-Graining of Molecular Dynamics without ForcesJournal of Chemical Theory and Computation, 2023
- Stochastic normalizing flows as non-equilibrium transformationsJournal of High Energy Physics, 2022
- Accurate Sampling of Macromolecular Conformations Using Adaptive Deep Learning and Coarse-Grained RepresentationJournal of Chemical Information and Modeling, 2022
- A validity test of the WCA perturbation theory for two-dimensional Lennard-Jones fluidsChemical Physics, 1992
- Phase diagram of the two-dimensional Lennard-Jones system; Evidence for first-order transitionsPhysica A: Statistical Mechanics and its Applications, 1981