Efficient Rare Event Sampling with Unsupervised Normalising Flows

Abstract: From Physics and Biology to Seismology and Economics, the behaviour of countless systems is determined by impactful yet unlikely transitions between metastable states known as \emph{rare events}, the study of which is essential for understanding and controlling these systems' properties. Classical computational methods to sample rare events remain prohibitively inefficient, and are a bottleneck for enhanced samplers requiring prior data. Here, we introduce a novel framework, FlowRES that uses unsupervised normalising flow neural networks to enhance Monte Carlo sampling of rare events by generating high-quality nonlocal Monte Carlo proposals. We validate FlowRES by sampling the transition path ensembles of equilibrium and non-equilibrium systems of Brownian particles exploring increasingly complex potential surfaces. Beyond eliminating requirements for prior data, FlowRES features key advantages over established samplers: no collective variables need defining, its efficiency remains constant even as events become increasingly unlikely, and it can handle systems with multiple routes between states.