Tangential Fixpoint Iterations for Gromov–Wasserstein Barycenters
- 28 April 2025
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Imaging Sciences
- Vol. 18 (2) , 1058-1100
Abstract
The Gromov–Wasserstein (GW) transport problem is a generalization of classic optimal transport, which seeks a transport between two measures while preserving their internal geometry. Due to meeting this theoretical underpinning, it is a valuable tool for the analysis of objects that do not possess a natural embedding or should be studied independently of it. Prime applications can thus be found in, e.g., shape matching, classification, and interpolation tasks. To tackle the latter, one theoretically justified approach is the employment of multimarginal GW transport and GW barycenters, which are Fréchet means with respect to the GW distance. However, because the computation of GW itself already poses a quadratic and nonconvex optimization problem, the determination of GW barycenters is a hard task, and algorithms for their computation are scarce. In this paper, we revisit a known procedure for the determination of Fréchet means in Riemannian manifolds via tangential approximations in the context of GW. We provide a characterization of barycenters in the GW tangent space, which ultimately gives rise to a fixpoint iteration for approximating GW barycenters using multimarginal plans. We propose a relaxation of this fixpoint iteration and show that it monotonously decreases the barycenter loss. In certain cases our proposed method naturally provides us with barycentric embeddings. The resulting algorithm is capable of producing qualitative shape interpolations between multiple 3D shapes with support sizes of over thousands of points in reasonable time. In addition, we verify our method on shape classification and multigraph matching tasks.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (RTG 2433 DAEDALUS)
This publication has 46 references indexed in Scilit:
- Parallelly Sliced Optimal Transport on Spheres and on the Rotation GroupJournal of Mathematical Imaging and Vision, 2024
- Simple approximative algorithms for free-support Wasserstein barycentersComputational Optimization and Applications, 2023
- Unbalanced Multi-marginal Optimal TransportJournal of Mathematical Imaging and Vision, 2022
- Curve Based Approximation of Measures on Manifolds by Discrepancy MinimizationFoundations of Computational Mathematics, 2021
- Lectures on Optimal Transport2021
- Introduction to Riemannian Manifolds2018
- Stochastic Processes and Applications2014
- Gromov–Wasserstein Distances and the Metric Approach to Object MatchingFoundations of Computational Mathematics, 2011
- Matching for teamsEconomic Theory, 2008
- Intrinsic Statistics on Riemannian Manifolds: Basic Tools for Geometric MeasurementsJournal of Mathematical Imaging and Vision, 2006