Dresden 2026 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
DY: Fachverband Dynamik und Statistische Physik
DY 14: Machine Learning in Dynamics and Statistical Physics II
DY 14.2: Vortrag
Montag, 9. März 2026, 15:15–15:30, HÜL/S186
Scalable Boltzmann Generators for equilibrium sampling of large-scale materials — •Maximilian Schebek1, Frank Noé1,2,3,4, and Jutta Rogal1,5 — 1Fachbereich Physik, Freie Universität Berlin, 14195 Berlin — 2Fachbereich Mathematik und Informatik, Freie Universität Berlin, 14195 Berlin — 3Microsoft Research AI for Science, 10178 Berlin — 4Department of Chemistry, Rice University, Houston, Texas 77005, USA — 5Initiative for Computational Catalysis, Flatiron Institute, New York, New York 10010, USA
Generating equilibrium ensembles is essential for modeling molecules and materials, yet traditional simulators like molecular dynamics suffer from limited sampling efficiency. Boltzmann Generators introduced the concept of one-shot deep learning for equilibrium sampling, but scalability to large systems has remained a major challenge. Here, we overcome this scaling limitation with a new Boltzmann Generator architecture that can model large materials systems. Our approach combines augmented coupling flows with graph neural networks to exploit local environments, enabling energy-based training and rapid inference. Compared to previous designs, it trains faster, uses fewer resources, and achieves superior sampling efficiency. Crucially, it transfers to much larger system sizes, allowing efficient sampling of materials with simulation cells exceeding a thousand atoms. We demonstrate its capabilities on Lennard-Jones crystals, mW water ice phases, and the silicon phase diagram, producing accurate equilibrium ensembles and free energies across scales where finite-size effects vanish.
Keywords: sampling; generative models; boltzmann generators; machine learning; statistical physics