Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional

Sanjeev Raja, Martin Sipka, Michael Psenka, Tobias Kreiman, Michal Pavelka, Aditi S. Krishnapriyan
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50972-51008, 2025.

Abstract

Transition path sampling (TPS), which involves finding probable paths connecting two points on an energy landscape, remains a challenge due to the complexity of real-world atomistic systems. Current machine learning approaches rely on expensive training procedures and under-utilize growing quantities of atomistic data, limiting scalability and generalization. Generative models of atomistic conformational ensembles sample temporally independent states from energy landscapes, but their application to TPS remains mostly unexplored. In this work, we address TPS by interpreting candidate paths as trajectories sampled from stochastic dynamics induced by the learned score function of generative models, namely denoising diffusion and flow matching. Under these dynamics, finding high-likelihood transition paths becomes equivalent to minimizing the Onsager-Machlup (OM) action functional, enabling us to repurpose pre-trained generative models for TPS in a zero-shot fashion. We demonstrate our approach on a Müller-Brown potential and several fast-folding proteins, where we obtain diverse, physically realistic transition pathways, as well as tetrapeptides, where we demonstrate successful TPS on systems not seen by the generative model during training. Our method can be easily incorporated into new generative models, making it practically relevant as models continue to scale and improve.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-raja25a, title = {Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional}, author = {Raja, Sanjeev and Sipka, Martin and Psenka, Michael and Kreiman, Tobias and Pavelka, Michal and Krishnapriyan, Aditi S.}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {50972--51008}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/raja25a/raja25a.pdf}, url = {https://proceedings.mlr.press/v267/raja25a.html}, abstract = {Transition path sampling (TPS), which involves finding probable paths connecting two points on an energy landscape, remains a challenge due to the complexity of real-world atomistic systems. Current machine learning approaches rely on expensive training procedures and under-utilize growing quantities of atomistic data, limiting scalability and generalization. Generative models of atomistic conformational ensembles sample temporally independent states from energy landscapes, but their application to TPS remains mostly unexplored. In this work, we address TPS by interpreting candidate paths as trajectories sampled from stochastic dynamics induced by the learned score function of generative models, namely denoising diffusion and flow matching. Under these dynamics, finding high-likelihood transition paths becomes equivalent to minimizing the Onsager-Machlup (OM) action functional, enabling us to repurpose pre-trained generative models for TPS in a zero-shot fashion. We demonstrate our approach on a Müller-Brown potential and several fast-folding proteins, where we obtain diverse, physically realistic transition pathways, as well as tetrapeptides, where we demonstrate successful TPS on systems not seen by the generative model during training. Our method can be easily incorporated into new generative models, making it practically relevant as models continue to scale and improve.} }
Endnote
%0 Conference Paper %T Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional %A Sanjeev Raja %A Martin Sipka %A Michael Psenka %A Tobias Kreiman %A Michal Pavelka %A Aditi S. Krishnapriyan %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-raja25a %I PMLR %P 50972--51008 %U https://proceedings.mlr.press/v267/raja25a.html %V 267 %X Transition path sampling (TPS), which involves finding probable paths connecting two points on an energy landscape, remains a challenge due to the complexity of real-world atomistic systems. Current machine learning approaches rely on expensive training procedures and under-utilize growing quantities of atomistic data, limiting scalability and generalization. Generative models of atomistic conformational ensembles sample temporally independent states from energy landscapes, but their application to TPS remains mostly unexplored. In this work, we address TPS by interpreting candidate paths as trajectories sampled from stochastic dynamics induced by the learned score function of generative models, namely denoising diffusion and flow matching. Under these dynamics, finding high-likelihood transition paths becomes equivalent to minimizing the Onsager-Machlup (OM) action functional, enabling us to repurpose pre-trained generative models for TPS in a zero-shot fashion. We demonstrate our approach on a Müller-Brown potential and several fast-folding proteins, where we obtain diverse, physically realistic transition pathways, as well as tetrapeptides, where we demonstrate successful TPS on systems not seen by the generative model during training. Our method can be easily incorporated into new generative models, making it practically relevant as models continue to scale and improve.
APA
Raja, S., Sipka, M., Psenka, M., Kreiman, T., Pavelka, M. & Krishnapriyan, A.S.. (2025). Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:50972-51008 Available from https://proceedings.mlr.press/v267/raja25a.html.

Related Material