FEAT: Free energy Estimators with Adaptive Transport
This work addresses a critical problem in scientific computing for researchers in fields like chemistry and physics, offering a principled foundation for neural free energy calculations, though it appears incremental relative to existing learning-based approaches.
The authors tackled the challenge of free energy estimation across scientific domains by developing FEAT, a framework that unifies equilibrium and non-equilibrium methods and provides consistent, minimum-variance estimators, demonstrating improvements over existing learning-based methods in experiments on toy examples, molecular simulations, and quantum field theory.
We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation -- a critical challenge across scientific domains. FEAT leverages learned transports implemented via stochastic interpolants and provides consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem, alongside variational upper and lower bounds on free energy differences. Unifying equilibrium and non-equilibrium methods under a single theoretical framework, FEAT establishes a principled foundation for neural free energy calculations. Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods. Our PyTorch implementation is available at https://github.com/jiajunhe98/FEAT.