Transition Path Sampling with Generative Models using Action Minimization

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 use expensive, task-specific, and data-free training procedures, limiting their ability to benefit from high-quality datasets and large-scale pre-trained models.

In this work, we address TPS by interpreting candidate paths as trajectories sampled from stochastic dynamics induced by the learned score function of pre-trained generative models, specifically denoising diffusion and flow matching. Under these dynamics, finding high-likelihood transition paths becomes equivalent to minimizing the Onsager–Machlup (OM) action functional.

This enables us to repurpose pre-trained generative models for TPS in a zero-shot manner, in contrast with bespoke, task-specific approaches in previous work. We demonstrate our approach on varied molecular systems, obtaining diverse, physically realistic transition pathways and generalizing beyond the pre-trained model’s original training dataset.

Our method can be easily incorporated into new generative models, making it practically relevant as models continue to scale and improve with increased data availability.

Our Speaker:

Sanjeev Raja

Sanjeev Raja is a 4th year PhD student in the Department of Electrical Engineering and Computer Science at the University of California, Berkeley, advised by Aditi Krishnapriyan.

He is also currently a part-time research intern at Valence Labs, based in Montreal. His research focuses on machine learning and generative modeling approaches to accelerate molecular sampling and simulation, with downstream applications in drug and materials discovery.