English

Dimensionality Reduction for Wasserstein Barycenter

Data Structures and Algorithms 2021-10-20 v2 Machine Learning Probability

Abstract

The Wasserstein barycenter is a geometric construct which captures the notion of centrality among probability distributions, and which has found many applications in machine learning. However, most algorithms for finding even an approximate barycenter suffer an exponential dependence on the dimension dd of the underlying space of the distributions. In order to cope with this "curse of dimensionality," we study dimensionality reduction techniques for the Wasserstein barycenter problem. When the barycenter is restricted to support of size nn, we show that randomized dimensionality reduction can be used to map the problem to a space of dimension O(logn)O(\log n) independent of both dd and kk, and that \emph{any} solution found in the reduced dimension will have its cost preserved up to arbitrary small error in the original space. We provide matching upper and lower bounds on the size of the reduced dimension, showing that our methods are optimal up to constant factors. We also provide a coreset construction for the Wasserstein barycenter problem that significantly decreases the number of input distributions. The coresets can be used in conjunction with random projections and thus further improve computation time. Lastly, our experimental results validate the speedup provided by dimensionality reduction while maintaining solution quality.

Keywords

Cite

@article{arxiv.2110.08991,
  title  = {Dimensionality Reduction for Wasserstein Barycenter},
  author = {Zachary Izzo and Sandeep Silwal and Samson Zhou},
  journal= {arXiv preprint arXiv:2110.08991},
  year   = {2021}
}

Comments

Published as a conference paper in NeurIPS 2021

R2 v1 2026-06-24T06:57:47.650Z