FEAT: Free energy Estimators with Adaptive Transport

arXiv:2504.11516 · stat.ML, cs.LG, physics.chem-ph, physics.comp-ph · Submitted 2025-04-15 · Read on arXiv

stat.ML, cs.LG, physics.chem-ph, physics.comp-ph

Submitted: 2025-04-15

Updated: 2026-09-26

Comments: Accepted to NeurIPS 2025; the first two authors contribute equally to this work; add an erratum to Appendix F.4 clarifying the applicability of the TSM loss

Code: https://github.com/jiajunhe98/FEAT

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Flow Matching — 10× in this paper · explained in 15 episodes
• Bennett Acceptance Ratio — 8× in this paper
• Thermodynamic Integration — 8× in this paper
• Hyperparameters — 7× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Normalizing Flow — 6× in this paper · explained in 3 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Parameterization — 4× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 10 episodes
• Normalizing Flows — 3× in this paper · explained in 4 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Generator — 2× in this paper · explained in 2 episodes
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Langevin Dynamics — 1× in this paper · explained in 3 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Optimal Transport (OT) — 1× in this paper · explained in 7 episodes
• Phase Transition — 1× in this paper · explained in 2 episodes
• Phase Transitions — 1× in this paper · explained in 2 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• NETS: A Non-Equilibrium Transport Sampler
• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
• Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
• Importance Weighted Autoencoders
• Target Score Matching
• Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
• Stochastic Variational Inference via Upper Bound
• Transferable Boltzmann Generators
• Learning Interpolations between Boltzmann Densities
• Solvation Free Energies from Neural Thermodynamic Integration
• Assessing generative modeling approaches for free energy estimates in condensed matter
• Towards Healing the Blindness of Score Matching

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier