Sampling the Liquid-Gas Critical Point with Boltzmann Generators

Abstract

Generative models based on invertible transformations provide a physics-aware route to sample equilibrium configurations directly from the Boltzmann distribution, enabling efficient exploration of complex thermodynamic landscapes. Here, we evaluate their applicability in regions where conventional simulations suffer from severe dynamical bottlenecks, focusing on the liquid-gas critical point of a Lennard-Jones fluid. We show that Boltzmann Generators capture essential signatures of critical behavior, retain reliable performance when trained at or near criticality, and extrapolate across neighboring states of the phase diagram. An intriguing observation is that the model's efficiency metric closely traces the underlying phase boundaries, hinting at a connection between generative performance and thermodynamics. However, the approach remains limited by the small system sizes currently accessible, which suppress the large fluctuations that characterize critical phenomena. Our results delineate the current capabilities and boundaries of Boltzmann Generators in challenging regions of phase space, while pointing toward future applications in problems dominated by slow dynamics, such as glass formation and nucleation.

References in corpus (16)

• Machine learning phases of matter
• Parallel Tempering: Theory, Applications, and New Perspectives
• Normalizing Flows: An Introduction and Review of Current Methods
• Crystal Nucleation in Liquids: Open Questions and Future Challenges in Molecular Dynamics Simulations
• Discovering Phase Transitions with Unsupervised Learning
• Pressure-energy correlations in liquids. I. Results from computer simulations
• Pressure-energy correlations in liquids. V. Isomorphs in generalized Lennard-Jones systems
• Modern computational studies of the glass transition
• Targeted free energy estimation via learned mappings
• Unsupervised learning universal critical behavior via the intrinsic dimension
• Roadmap on machine learning glassy dynamics
• Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
• Free energy calculation of crystalline solids using normalizing flow
• Efficient Rare Event Sampling with Unsupervised Normalising Flows
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• Efficient mapping of phase diagrams with conditional Boltzmann Generators