Unbalanced Diffusion Schrödinger Bridge

by   Matteo Pariset, et al.

Schrödinger bridges (SBs) provide an elegant framework for modeling the temporal evolution of populations in physical, chemical, or biological systems. Such natural processes are commonly subject to changes in population size over time due to the emergence of new species or birth and death events. However, existing neural parameterizations of SBs such as diffusion Schrödinger bridges (DSBs) are restricted to settings in which the endpoints of the stochastic process are both probability measures and assume conservation of mass constraints. To address this limitation, we introduce unbalanced DSBs which model the temporal evolution of marginals with arbitrary finite mass. This is achieved by deriving the time reversal of stochastic differential equations with killing and birth terms. We present two novel algorithmic schemes that comprise a scalable objective function for training unbalanced DSBs and provide a theoretical analysis alongside challenging applications on predicting heterogeneous molecular single-cell responses to various cancer drugs and simulating the emergence and spread of new viral variants.


page 9

page 31


Improved estimations of stochastic chemical kinetics by finite state expansion

Quantitative mechanistic models based on reaction networks with stochast...

Neural Unbalanced Optimal Transport via Cycle-Consistent Semi-Couplings

Comparing unpaired samples of a distribution or population taken at diff...

Dirichlet Diffusion Score Model for Biological Sequence Generation

Designing biological sequences is an important challenge that requires s...

Stationary distributions of persistent ecological systems

We analyze ecological systems that are influenced by random environmenta...

Recovering Stochastic Dynamics via Gaussian Schrödinger Bridges

We propose a new framework to reconstruct a stochastic process {ℙ_t: t ∈...

Aligned Diffusion Schrödinger Bridges

Diffusion Schrödinger bridges (DSB) have recently emerged as a powerful ...

Mass-preserving approximation of a chemotaxis multi-domain transmission model for microfluidic chips

The present work was inspired by the recent developments in laboratory e...

Please sign up or login with your details

Forgot password? Click here to reset