Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.16634 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917279586844672 |
|---|---|
| author | Xie, Yu Winkler, Ludwig Sun, Lixin Lewis, Sarah Foster, Adam E. Luna, José Jiménez Hempel, Tim Gastegger, Michael Chen, Yaoyi Zaporozhets, Iryna Clementi, Cecilia Bishop, Christopher M. Noé, Frank |
| author_facet | Xie, Yu Winkler, Ludwig Sun, Lixin Lewis, Sarah Foster, Adam E. Luna, José Jiménez Hempel, Tim Gastegger, Michael Chen, Yaoyi Zaporozhets, Iryna Clementi, Cecilia Bishop, Christopher M. Noé, Frank |
| contents | The rare-event sampling problem has long been the central limiting factor in molecular dynamics (MD), especially in biomolecular simulation. Recently, diffusion models such as BioEmu have emerged as powerful equilibrium samplers that generate independent samples from complex molecular distributions, eliminating the cost of sampling rare transition events. However, a sampling problem remains when computing observables that rely on states which are rare in equilibrium, for example folding free energies. Here, we introduce enhanced diffusion sampling, enabling efficient exploration of rare-event regions while preserving unbiased thermodynamic estimators. The key idea is to perform quantitatively accurate steering protocols to generate biased ensembles and subsequently recover equilibrium statistics via exact reweighting. We instantiate our framework in three algorithms: UmbrellaDiff (umbrella sampling with diffusion models), $Δ$G-Diff (free-energy differences via tilted ensembles), and MetaDiff (a batchwise analogue for metadynamics). Across toy systems, protein folding landscapes and folding free energies, our methods achieve fast, accurate, and scalable estimation of equilibrium properties within GPU-minutes to hours per system -- closing the rare-event sampling gap that remained after the advent of diffusion-model equilibrium samplers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16634 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models Xie, Yu Winkler, Ludwig Sun, Lixin Lewis, Sarah Foster, Adam E. Luna, José Jiménez Hempel, Tim Gastegger, Michael Chen, Yaoyi Zaporozhets, Iryna Clementi, Cecilia Bishop, Christopher M. Noé, Frank Machine Learning Artificial Intelligence Biological Physics Chemical Physics The rare-event sampling problem has long been the central limiting factor in molecular dynamics (MD), especially in biomolecular simulation. Recently, diffusion models such as BioEmu have emerged as powerful equilibrium samplers that generate independent samples from complex molecular distributions, eliminating the cost of sampling rare transition events. However, a sampling problem remains when computing observables that rely on states which are rare in equilibrium, for example folding free energies. Here, we introduce enhanced diffusion sampling, enabling efficient exploration of rare-event regions while preserving unbiased thermodynamic estimators. The key idea is to perform quantitatively accurate steering protocols to generate biased ensembles and subsequently recover equilibrium statistics via exact reweighting. We instantiate our framework in three algorithms: UmbrellaDiff (umbrella sampling with diffusion models), $Δ$G-Diff (free-energy differences via tilted ensembles), and MetaDiff (a batchwise analogue for metadynamics). Across toy systems, protein folding landscapes and folding free energies, our methods achieve fast, accurate, and scalable estimation of equilibrium properties within GPU-minutes to hours per system -- closing the rare-event sampling gap that remained after the advent of diffusion-model equilibrium samplers. |
| title | Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models |
| topic | Machine Learning Artificial Intelligence Biological Physics Chemical Physics |
| url | https://arxiv.org/abs/2602.16634 |