Saved in:
Bibliographic Details
Main Authors: Beier, Florian, Piening, Moritz, Beinert, Robert, Steidl, Gabriele
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.07510
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We propose a new approach for unsupervised alignment of heterogeneous datasets, which maps data from two different domains without any known correspondences to a common metric space. Our method is based on an unbalanced optimal transport problem with Gromov-Wasserstein marginal penalization. It can be seen as a counterpart to the recently introduced joint multidimensional scaling method. We prove that there exists a minimizer of our functional and that for penalization parameters going to infinity, the corresponding sequence of minimizers converges to a minimizer of the so-called embedded Wasserstein distance. Our model can be reformulated as a quadratic, multi-marginal, unbalanced optimal transport problem, for which a bi-convex relaxation admits a numerical solver via block-coordinate descent. We provide numerical examples for joint embeddings in Euclidean as well as non-Euclidean spaces.