Coarse-Grained Boltzmann Generators
This work addresses a longstanding problem in computational chemistry for researchers needing unbiased sampling of larger molecular systems, representing an incremental improvement by combining existing methods.
The paper tackles the challenge of sampling equilibrium molecular configurations from the Boltzmann distribution by proposing Coarse-Grained Boltzmann Generators (CG-BGs), which unify scalable reduced-order modeling with exact importance sampling to capture complex interactions in larger systems.
Sampling equilibrium molecular configurations from the Boltzmann distribution is a longstanding challenge. Boltzmann Generators (BGs) address this by combining exact-likelihood generative models with importance sampling, but their practical scalability is limited. Meanwhile, coarse-grained surrogates enable the modeling of larger systems by reducing effective dimensionality, yet often lack the reweighting process required to ensure asymptotically correct statistics. In this work, we propose Coarse-Grained Boltzmann Generators (CG-BGs), a principled framework that unifies scalable reduced-order modeling with the exactness of importance sampling. CG-BGs act in a coarse-grained coordinate space, using a learned potential of mean force (PMF) to reweight samples generated by a flow-based model. Crucially, we show that this PMF can be efficiently learned from rapidly converged data via force matching. Our results demonstrate that CG-BGs faithfully capture complex interactions mediated by explicit solvent within highly reduced representations, establishing a scalable pathway for the unbiased sampling of larger molecular systems.