Score: 1

Branched Schrödinger Bridge Matching

Published: June 10, 2025 | arXiv ID: 2506.09007v1

By: Sophia Tang , Yinuo Zhang , Alexander Tong and more

Potential Business Impact:

Helps AI learn many different paths from one start.

Business Areas:
A/B Testing Data and Analytics

Predicting the intermediate trajectories between an initial and target distribution is a central problem in generative modeling. Existing approaches, such as flow matching and Schr\"odinger Bridge Matching, effectively learn mappings between two distributions by modeling a single stochastic path. However, these methods are inherently limited to unimodal transitions and cannot capture branched or divergent evolution from a common origin to multiple distinct outcomes. To address this, we introduce Branched Schr\"odinger Bridge Matching (BranchSBM), a novel framework that learns branched Schr\"odinger bridges. BranchSBM parameterizes multiple time-dependent velocity fields and growth processes, enabling the representation of population-level divergence into multiple terminal distributions. We show that BranchSBM is not only more expressive but also essential for tasks involving multi-path surface navigation, modeling cell fate bifurcations from homogeneous progenitor states, and simulating diverging cellular responses to perturbations.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
40 pages

Category
Computer Science:
Machine Learning (CS)