Tree-Based Diffusion Schr\"odinger Bridge with Applications to Wasserstein Barycenters
Noble, Maxence, De Bortoli, Valentin, Doucet, Arnaud, Durmus, Alain
Multi-marginal Optimal Transport (mOT), a generalization of OT, aims at minimizing the integral of a cost function with respect to a distribution with some prescribed marginals. In this paper, we consider an entropic version of mOT with a tree-structured quadratic cost, i.e., a function that can be written as a sum of pairwise cost functions between the nodes of a tree. To address this problem, we develop Tree-based Diffusion Schr\"odinger Bridge (TreeDSB), an extension of the Diffusion Schr\"odinger Bridge (DSB) algorithm. TreeDSB corresponds to a dynamic and continuous state-space counterpart of the multimarginal Sinkhorn algorithm. A notable use case of our methodology is to compute Wasserstein barycenters which can be recast as the solution of a mOT problem on a star-shaped tree. We demonstrate that our methodology can be applied in high-dimensional settings such as image interpolation and Bayesian fusion.
Oct-28-2023
- Country:
- North America > Canada (0.27)
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Health & Medicine (0.45)
- Technology: