Gromov-Wasserstein Barycenters: The Analysis Problem
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912987048050688 |
|---|---|
| author | Martín, Rocío Díaz Medri, Ivan V. Murphy, James M. |
| author_facet | Martín, Rocío Díaz Medri, Ivan V. Murphy, James M. |
| contents | This paper considers the problem of estimating a matrix that encodes pairwise distances in a finite metric space (or, more generally, the edge weight matrix of a network) under the barycentric coding model (BCM) with respect to the Gromov-Wasserstein (GW) distance function. We frame this task as estimating the unknown barycentric coordinates with respect to the GW distance, assuming that the target matrix (or kernel) belongs to the set of GW barycenters of a finite collection of known templates. In the language of harmonic analysis, if computing GW barycenters can be viewed as a synthesis problem, this paper aims to solve the corresponding analysis problem. We propose two methods: one utilizing fixed-point iteration for computing GW barycenters, and another employing a differentiation-based approach to the GW structure using a blow-up technique. Finally, we demonstrate the application of the proposed GW analysis approach in a series of numerical experiments and applications to machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09865 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gromov-Wasserstein Barycenters: The Analysis Problem Martín, Rocío Díaz Medri, Ivan V. Murphy, James M. Optimization and Control Numerical Analysis Functional Analysis Metric Geometry 42B99, 49Q22, 68T01, 68T09, 90C35, 94A12 This paper considers the problem of estimating a matrix that encodes pairwise distances in a finite metric space (or, more generally, the edge weight matrix of a network) under the barycentric coding model (BCM) with respect to the Gromov-Wasserstein (GW) distance function. We frame this task as estimating the unknown barycentric coordinates with respect to the GW distance, assuming that the target matrix (or kernel) belongs to the set of GW barycenters of a finite collection of known templates. In the language of harmonic analysis, if computing GW barycenters can be viewed as a synthesis problem, this paper aims to solve the corresponding analysis problem. We propose two methods: one utilizing fixed-point iteration for computing GW barycenters, and another employing a differentiation-based approach to the GW structure using a blow-up technique. Finally, we demonstrate the application of the proposed GW analysis approach in a series of numerical experiments and applications to machine learning. |
| title | Gromov-Wasserstein Barycenters: The Analysis Problem |
| topic | Optimization and Control Numerical Analysis Functional Analysis Metric Geometry 42B99, 49Q22, 68T01, 68T09, 90C35, 94A12 |
| url | https://arxiv.org/abs/2507.09865 |