Path Gradients after Flow Matching
This incremental improvement addresses sampling bottlenecks in molecular simulations for researchers in computational chemistry and drug discovery.
The paper tackles the problem of improving sampling efficiency in Boltzmann Generators for molecular systems by fine-tuning Continuous Normalizing Flows (CNFs) trained with Flow Matching using path gradients, resulting in up to a threefold increase in sampling efficiency without additional computational cost.
Boltzmann Generators have emerged as a promising machine learning tool for generating samples from equilibrium distributions of molecular systems using Normalizing Flows and importance weighting. Recently, Flow Matching has helped speed up Continuous Normalizing Flows (CNFs), scale them to more complex molecular systems, and minimize the length of the flow integration trajectories. We investigate the benefits of using path gradients to fine-tune CNFs initially trained by Flow Matching, in the setting where a target energy is known. Our experiments show that this hybrid approach yields up to a threefold increase in sampling efficiency for molecular systems, all while using the same model, a similar computational budget and without the need for additional sampling. Furthermore, by measuring the length of the flow trajectories during fine-tuning, we show that path gradients largely preserve the learned structure of the flow.