Corpus ID: 211296373

Variational Wasserstein Barycenters for Geometric Clustering

  title={Variational Wasserstein Barycenters for Geometric Clustering},
  author={Liang Mi and Tianshu Yu and Jos{\'e} Bento and Wen Zhang and Baoxin Li and Yalin Wang},
We propose to compute Wasserstein barycenters (WBs) by solving for Monge maps with variational principle. We discuss the metric properties of WBs and explore their connections, especially the connections of Monge WBs, to K-means clustering and co-clustering. We also discuss the feasibility of Monge WBs on unbalanced measures and spherical domains. We propose two new problems -- regularized K-means and Wasserstein barycenter compression. We demonstrate the use of VWBs in solving these clustering… Expand
Distributed Optimization with Quantization for Computing Wasserstein Barycenters
This work proposes a sampling gradient quantization scheme that allows efficient communication and computation of approximate barycenters where the factor distributions are stored distributedly on arbitrary networks. Expand
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
This work presents a novel scalable algorithm to approximate the Wasserstein Barycenter aiming at high-dimensional applications in machine learning, based on the Kantorovich dual formulation of the 2-Wasserstein distance as well as a recent neural network architecture, input convex neural network, that is known to parametrize convex functions. Expand


Stochastic Wasserstein Barycenters
This work presents a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport that can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations. Expand
Variational Wasserstein Clustering
A new clustering method based on optimal transportation that simultaneously pursue clustering and the Wasserstein distance between the centroids and the target domain, resulting in a measure-preserving mapping. Expand
Fast Computation of Wasserstein Barycenters
The Wasserstein distance is proposed to be smoothed with an entropic regularizer and recover in doing so a strictly convex objective whose gradients can be computed for a considerably cheaper computational cost using matrix scaling algorithms. Expand
Barycenters in the Wasserstein Space
This paper provides existence, uniqueness, characterizations, and regularity of the barycenter and relates it to the multimarginal optimal transport problem considered by Gangbo and Świech in [Comm. Pure Appl. Math., 51 (1998), pp. 23–45]. Expand
Regularized Wasserstein Means for Aligning Distributional Data
This work raises the problem of regularizing Wasserstein means and proposes several terms tailored to tackle different problems, based on the variational transportation to distribute a sparse discrete measure into the target domain. Expand
Multilevel Clustering via Wasserstein Means
We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially largeExpand
Fast Discrete Distribution Clustering Using Wasserstein Barycenter With Sparse Support
A modified Bregman ADMM approach for computing the approximate discrete Wasserstein barycenter of large clusters that achieves high accuracy empirically at a much reduced computational cost and is highly competitive in comparison with some widely used methods in the corresponding areas. Expand
Approximation of Wasserstein distance with Transshipment
An algorithm for approximating the p-Wasserstein distance between histograms defined on unstructured discrete grids is presented. It is based on the computation of a barycenter constrained to beExpand
Parallel Streaming Wasserstein Barycenters
This work presents a scalable, communication-efficient, parallel algorithm for computing the Wasserstein barycenter of arbitrary distributions, which can operate directly on continuous input distributions and is optimized for streaming data. Expand
Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphs
This paper presents a novel method to compute the exact Kantorovich-Wasserstein distance between a pair of $d$-dimensional histograms having $n$ bins each. We prove that this problem is equivalent toExpand