Name
Abstract | ||
|---|---|---|
Optimal transport (OT) is a powerful tool for measuring the distance between two probability distributions. In this paper, we introduce a new manifold named as the coupling matrix manifold (CMM), where each point on this novel manifold can be regarded as a transportation plan of the optimal transport problem. We firstly explore the Riemannian geometry of CMM with the metric expressed by the Fisher information. These geometrical features can be exploited in many essential optimization methods as a framework solving all types of OT problems via incorporating numerical Riemannian optimization algorithms such as gradient descent and trust region algorithms in CMM manifold. The proposed approach is validated using several OT problems in comparison with recent state-of-the-art related works. For the classic OT problem and its entropy regularized variant, it is shown that our method is comparable with the classic algorithms such as linear programming and Sinkhorn algorithms. For other types of non-entropy regularized OT problems, our proposed method has shown superior performance to other works, whereby the geometric information of the OT feasible space was not incorporated within. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1007/s10994-020-05931-2 | MACHINE LEARNING |
Keywords | DocType | Volume |
Optimal transport, Doubly stochastic matrices, Coupling matrix manifold, Sinkhorn algorithm, Wasserstein distance, Entropy regularized optimal transport | Journal | 110 |
Issue | ISSN | Citations |
3 | 0885-6125 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dai Shi | 1 | 0 | 0.34 |
| Junbin Gao | 2 | 55 | 8.87 |
| X. Hong | 3 | 157 | 11.12 |
| S. T. Boris Choy | 4 | 0 | 0.34 |
| Zhiyong Wang | 5 | 550 | 51.76 |