Simulation-Free Structure Learning For Stochastic Dynamics

Noah El Rimawi-Fine, Adam Stecklov, Lucas Nelson, Alexander Tong, Mathieu Blanchette, Stephen Y. Zhang, Lazar Atanackovic

Track: Tiny Paper Track

Keywords: flow matching, schrodinger bridge, gene regulatory network

Abstract:

We introduce a principled approach for jointly recovering the underlying network
structure and dynamic response of a physical system. We show that our simulation-free method,
NGM-SF2M, not only exhibits improved scaling relative to NGM on progressively larger linear
systems, but also consistently retrieves a competitive recovery of the underlying network structure.
Moreover, we show that incorporating interventional data yields improved performance for inferring
network interactions. Our results indicate that while RF recovers marginally more accurate network
structure, NGM-SF2M yields improved performance on the joint task – dynamical inference and
structure learning. In future work, we aim to extend our framework to higher-dimensional systems,
real-world settings, and integrate multi-modal data such as chromatin accessibility.

Attendance: Lazar Atanackovic

Submission Number: 86