Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.08117 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917800088436736 |
|---|---|
| author | Nguyen, Ngoc-Hai Le, Dung Nguyen, Hoang-Phi Pham, Tung Ho, Nhat |
| author_facet | Nguyen, Ngoc-Hai Le, Dung Nguyen, Hoang-Phi Pham, Tung Ho, Nhat |
| contents | We explore a robust version of the barycenter problem among $n$ centered Gaussian probability measures, termed Semi-Unbalanced Optimal Transport (SUOT)-based Barycenter, wherein the barycenter remains fixed while the others are relaxed using Kullback-Leibler divergence. We develop optimization algorithms on Bures-Wasserstein manifold, named the Exact Geodesic Gradient Descent and Hybrid Gradient Descent algorithms. While the Exact Geodesic Gradient Descent method is based on computing the exact closed form of the first-order derivative of the objective function of the barycenter along a geodesic on the Bures manifold, the Hybrid Gradient Descent method utilizes optimizer components when solving the SUOT problem to replace outlier measures before applying the Riemannian Gradient Descent. We establish the theoretical convergence guarantees for both methods and demonstrate that the Exact Geodesic Gradient Descent algorithm attains a dimension-free convergence rate. Finally, we conduct experiments to compare the normal Wasserstein Barycenter with ours and perform an ablation study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08117 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Barycenter Computation: Semi-Unbalanced Optimal Transport-based Method on Gaussians Nguyen, Ngoc-Hai Le, Dung Nguyen, Hoang-Phi Pham, Tung Ho, Nhat Machine Learning 62-08 G.1.6; F.2.1 We explore a robust version of the barycenter problem among $n$ centered Gaussian probability measures, termed Semi-Unbalanced Optimal Transport (SUOT)-based Barycenter, wherein the barycenter remains fixed while the others are relaxed using Kullback-Leibler divergence. We develop optimization algorithms on Bures-Wasserstein manifold, named the Exact Geodesic Gradient Descent and Hybrid Gradient Descent algorithms. While the Exact Geodesic Gradient Descent method is based on computing the exact closed form of the first-order derivative of the objective function of the barycenter along a geodesic on the Bures manifold, the Hybrid Gradient Descent method utilizes optimizer components when solving the SUOT problem to replace outlier measures before applying the Riemannian Gradient Descent. We establish the theoretical convergence guarantees for both methods and demonstrate that the Exact Geodesic Gradient Descent algorithm attains a dimension-free convergence rate. Finally, we conduct experiments to compare the normal Wasserstein Barycenter with ours and perform an ablation study. |
| title | On Barycenter Computation: Semi-Unbalanced Optimal Transport-based Method on Gaussians |
| topic | Machine Learning 62-08 G.1.6; F.2.1 |
| url | https://arxiv.org/abs/2410.08117 |