Normalizing flows for atomic solids
Peter Wirnsberger, George Papamakarios, Borja Ibarz et al. · Machine Learning Science and Technology · 2022
Abstract We present a machine-learning approach, based on normalizing flows, for modelling atomic solids. Our model transforms an analytically tractable base distribution into the target solid without requiring ground-truth samples for training. We report Helmholtz free energy estimates for cubic and hexagonal ice modelled as monatomic water as well as for a truncated and shifted Lennard-Jones system, and find them to be in excellent agreement with literature values and with estimates from established baseline methods. We further investigate structural properties and show that the model samples are nearly indistinguishable from the ones obtained with molecular dynamics. Our results thus demonstrate that normalizing flows can provide high-quality samples and free energy estimates without the need for multi-staging.
Cited by 41 works. doi:10.1088/2632-2153/ac6b16 Open-access PDF
Authors
- Peter Wirnsberger
- George Papamakarios
- Borja Ibarz
- Sébastien Racanière
- Andrew J. Ballard
- Alexander Pritzel
- Charles Blundell
References
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Attention Is All You Need
- Hybrid Monte Carlo
- Understanding Molecular Simulation
- LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales
- Efficient estimation of free energy differences from Monte Carlo data
- New Monte Carlo method to compute the free energy of arbitrary solids. Application to the fcc and hcp phases of hard spheres
- Variational Inference with Normalizing Flows
- Prediction of absolute crystal-nucleation rate in hard-sphere colloids
- Statistically optimal analysis of samples from multiple equilibrium states