Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore a comprehensive lecture on "Free energy Estimators with Adaptive Transport (FEAT)" presented by Yuanqi Du and Jiajun He from Valence Labs. This one-hour talk introduces a novel framework for tackling free energy estimation, a fundamental challenge across scientific domains. Learn how FEAT leverages learned transports implemented via stochastic interpolants to provide consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem. The presenters explain how FEAT unifies equilibrium and non-equilibrium methods under a single theoretical framework, establishing a principled foundation for neural free energy calculations. The lecture covers experimental validation on toy examples, molecular simulations, and quantum field theory, demonstrating FEAT's improvements over existing learning-based methods. This presentation is part of Portal, the home of the AI for drug discovery community, where viewers can connect with speakers and access additional resources.
