Coupling Matrix Manifolds and Their Applications in Optimal Transport
arXiv:1911.06905
Abstract
Optimal transport (OT) is a powerful tool for measuring the distance between two defined probability distributions. In this paper, we develop a new manifold named the coupling matrix manifold (CMM), where each point on CMM can be regarded as the transportation plan of the OT problem. We firstly explore the Riemannian geometry of CMM with the metric expressed by the Fisher information. These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems. The proposed method is then applied to solve several OT problems studied by previous literature. The results of the numerical experiments illustrate that the optimization algorithms that are based on the method proposed in this paper are comparable to the classic ones, for example, the Sinkhorn algorithm, while outperforming other state-of-the-art algorithms without considering the geometry information, especially in the case of non-entropy optimal transport.
References in corpus (9)
- Improved Training of Wasserstein GANs
- Fast Computation of Wasserstein Barycenters
- Learning with a Wasserstein Loss
- Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
- Stochastic Optimization for Large-scale Optimal Transport
- From optimal transport to generative modeling: the VEGAN cookbook
- Manifold Optimization Over the Set of Doubly Stochastic Matrices: A Second-Order Geometry
- Convex Color Image Segmentation with Optimal Transport Distances
- Wasserstein-Wasserstein Auto-Encoders