2023/05/26 by Maxence Noble, Valentin De Bortoli, Noble, Maxence +5 · 5 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Connexins and lens biology #FOS: Computer and information sciences #FOS: Mathematics #Heat shock proteins research #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)
paper · pdf · doi:10.48550/arxiv.2305.16557
openalex publication_date 2023/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
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 Schrödinger Bridge (TreeDSB), an extension of the Diffusion Schrödinger 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.