Tree-Sliced Wasserstein Distance with Nonlinear Projection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916783701622784 |
|---|---|
| author | Tran, Thanh Tran, Viet-Hoang Chu, Thanh Pham, Trang Ghaoui, Laurent El Le, Tam Nguyen, Tan M. |
| author_facet | Tran, Thanh Tran, Viet-Hoang Chu, Thanh Pham, Trang Ghaoui, Laurent El Le, Tam Nguyen, Tan M. |
| contents | Tree-Sliced methods have recently emerged as an alternative to the traditional Sliced Wasserstein (SW) distance, replacing one-dimensional lines with tree-based metric spaces and incorporating a splitting mechanism for projecting measures. This approach enhances the ability to capture the topological structures of integration domains in Sliced Optimal Transport while maintaining low computational costs. Building on this foundation, we propose a novel nonlinear projectional framework for the Tree-Sliced Wasserstein (TSW) distance, substituting the linear projections in earlier versions with general projections, while ensuring the injectivity of the associated Radon Transform and preserving the well-definedness of the resulting metric. By designing appropriate projections, we construct efficient metrics for measures on both Euclidean spaces and spheres. Finally, we validate our proposed metric through extensive numerical experiments for Euclidean and spherical datasets. Applications include gradient flows, self-supervised learning, and generative models, where our methods demonstrate significant improvements over recent SW and TSW variants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00968 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tree-Sliced Wasserstein Distance with Nonlinear Projection Tran, Thanh Tran, Viet-Hoang Chu, Thanh Pham, Trang Ghaoui, Laurent El Le, Tam Nguyen, Tan M. Machine Learning Artificial Intelligence Tree-Sliced methods have recently emerged as an alternative to the traditional Sliced Wasserstein (SW) distance, replacing one-dimensional lines with tree-based metric spaces and incorporating a splitting mechanism for projecting measures. This approach enhances the ability to capture the topological structures of integration domains in Sliced Optimal Transport while maintaining low computational costs. Building on this foundation, we propose a novel nonlinear projectional framework for the Tree-Sliced Wasserstein (TSW) distance, substituting the linear projections in earlier versions with general projections, while ensuring the injectivity of the associated Radon Transform and preserving the well-definedness of the resulting metric. By designing appropriate projections, we construct efficient metrics for measures on both Euclidean spaces and spheres. Finally, we validate our proposed metric through extensive numerical experiments for Euclidean and spherical datasets. Applications include gradient flows, self-supervised learning, and generative models, where our methods demonstrate significant improvements over recent SW and TSW variants. |
| title | Tree-Sliced Wasserstein Distance with Nonlinear Projection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.00968 |