Projection Robust Wasserstein Barycenter

by   Minhui Huang, et al.

Collecting and aggregating information from several probability measures or histograms is a fundamental task in machine learning. One of the popular solution methods for this task is to compute the barycenter of the probability measures under the Wasserstein metric. However, approximating the Wasserstein barycenter is numerically challenging because of the curse of dimensionality. This paper proposes the projection robust Wasserstein barycenter (PRWB) that mitigates the curse of dimensionality. This new model projects the probability measures onto a lower-dimensional subspace that maximizes the Wasserstein barycenter objective. The resulting problem is a max-min problem over the Stiefel manifold, which is numerically challenging in practice. Combining the iterative Bregman projection algorithm and Riemannian optimization, we propose two new algorithms for computing the PRWB. The complexity of arithmetic operations of the proposed algorithms for obtaining an ϵ-stationary solution is analyzed. We incorporate the PRWB into a discrete distribution clustering algorithm, and the numerical results on real text datasets confirm that our PRWB model helps improve the clustering performance significantly.


page 1

page 2

page 3

page 4


A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance

The Wasserstein distance has become increasingly important in machine le...

Stochastic Saddle-Point Optimization for Wasserstein Barycenters

We study the computation of non-regularized Wasserstein barycenters of p...

Projection Robust Wasserstein Distance and Riemannian Optimization

Projection robust Wasserstein (PRW) distance, or Wasserstein projection ...

Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning

In this paper, we propose Wasserstein Isometric Mapping (Wassmap), a par...

Penalization of barycenters for φ-exponential distributions

In this paper we study the penalization of barycenters in the Wasserstei...

Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution

The conventional sliced Wasserstein is defined between two probability m...

Computational Hardness and Fast Algorithm for Fixed-Support Wasserstein Barycenter

We study in this paper the fixed-support Wasserstein barycenter problem ...