Aligned Diffusion Schrödinger Bridges

by   Vignesh Ram Somnath, et al.

Diffusion Schrödinger bridges (DSB) have recently emerged as a powerful framework for recovering stochastic dynamics via their marginal observations at different time points. Despite numerous successful applications, existing algorithms for solving DSBs have so far failed to utilize the structure of aligned data, which naturally arises in many biological phenomena. In this paper, we propose a novel algorithmic framework that, for the first time, solves DSBs while respecting the data alignment. Our approach hinges on a combination of two decades-old ideas: The classical Schrödinger bridge theory and Doob's h-transform. Compared to prior methods, our approach leads to a simpler training procedure with lower variance, which we further augment with principled regularization schemes. This ultimately leads to sizeable improvements across experiments on synthetic and real data, including the tasks of rigid protein docking and temporal evolution of cellular differentiation processes.


page 5

page 6

page 8

page 13


Simulating Diffusion Bridges with Score Matching

We consider the problem of simulating diffusion bridges, i.e. diffusion ...

Diffusion State Distances: Multitemporal Analysis, Fast Algorithms, and Applications to Biological Networks

Data-dependent metrics are powerful tools for learning the underlying st...

SE(3) diffusion model with application to protein backbone generation

The design of novel protein structures remains a challenge in protein en...

Unbalanced Diffusion Schrödinger Bridge

Schrödinger bridges (SBs) provide an elegant framework for modeling the ...

Diffusion Models for Constrained Domains

Denoising diffusion models are a recent class of generative models which...

Improved sampling via learned diffusions

Recently, a series of papers proposed deep learning-based approaches to ...

Please sign up or login with your details

Forgot password? Click here to reset