Boltzmann Generators -- Sampling Equilibrium States of Many-Body Systems with Deep Learning

Abstract

Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge. Lacking methods for generating statistically independent equilibrium samples in "one shot", vast computational effort is invested for simulating these system in small steps, e.g., using Molecular Dynamics. Combining deep learning and statistical mechanics, we here develop Boltzmann Generators, that are shown to generate unbiased one-shot equilibrium samples of representative condensed matter systems and proteins. Boltzmann Generators use neural networks to learn a coordinate transformation of the complex configurational equilibrium distribution to a distribution that can be easily sampled. Accurate computation of free energy differences and discovery of new configurations are demonstrated, providing a statistical mechanics tool that can avoid rare events during sampling without prior knowledge of reaction coordinates.

Cited by in corpus (8)

• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models
• Differentiable Molecular Simulations for Control and Learning
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests
• Harmonic Path Integral Diffusion
• Understanding ML driven HPC: Applications and Infrastructure