Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918379292459008 |
|---|---|
| author | Montesuma, Eduardo Fernandes Bendou, Yassir Gartrell, Mike |
| author_facet | Montesuma, Eduardo Fernandes Bendou, Yassir Gartrell, Mike |
| contents | Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not scalable as they assume access to the complete set of samples from the input measures. Meanwhile, neural network approaches do scale well, but rely on complex optimization problems and cannot easily incorporate label information. We address these limitations through gradient flows in the space of probability measures. Through time discretization, we achieve a scalable algorithm that i) relies on mini-batch optimal transport, ii) accepts modular regularization through task-aware functions, and iii) seamlessly integrates supervised information into the ground-cost. We empirically validate our approach on domain adaptation benchmarks that span computer vision, neuroscience, and chemical engineering. Our method establishes a new state-of-the-art barycenter solver, with labeled barycenters consistently outperforming unlabeled ones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation Montesuma, Eduardo Fernandes Bendou, Yassir Gartrell, Mike Machine Learning Artificial Intelligence Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not scalable as they assume access to the complete set of samples from the input measures. Meanwhile, neural network approaches do scale well, but rely on complex optimization problems and cannot easily incorporate label information. We address these limitations through gradient flows in the space of probability measures. Through time discretization, we achieve a scalable algorithm that i) relies on mini-batch optimal transport, ii) accepts modular regularization through task-aware functions, and iii) seamlessly integrates supervised information into the ground-cost. We empirically validate our approach on domain adaptation benchmarks that span computer vision, neuroscience, and chemical engineering. Our method establishes a new state-of-the-art barycenter solver, with labeled barycenters consistently outperforming unlabeled ones. |
| title | Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04602 |