English

Sinkhorn Barycenter via Functional Gradient Descent

Machine Learning 2020-07-22 v1 Machine Learning

Abstract

In this paper, we consider the problem of computing the barycenter of a set of probability distributions under the Sinkhorn divergence. This problem has recently found applications across various domains, including graphics, learning, and vision, as it provides a meaningful mechanism to aggregate knowledge. Unlike previous approaches which directly operate in the space of probability measures, we recast the Sinkhorn barycenter problem as an instance of unconstrained functional optimization and develop a novel functional gradient descent method named Sinkhorn Descent (SD). We prove that SD converges to a stationary point at a sublinear rate, and under reasonable assumptions, we further show that it asymptotically finds a global minimizer of the Sinkhorn barycenter problem. Moreover, by providing a mean-field analysis, we show that SD preserves the weak convergence of empirical measures. Importantly, the computational complexity of SD scales linearly in the dimension dd and we demonstrate its scalability by solving a 100100-dimensional Sinkhorn barycenter problem.

Keywords

Cite

@article{arxiv.2007.10449,
  title  = {Sinkhorn Barycenter via Functional Gradient Descent},
  author = {Zebang Shen and Zhenfu Wang and Alejandro Ribeiro and Hamed Hassani},
  journal= {arXiv preprint arXiv:2007.10449},
  year   = {2020}
}

Comments

submitted to NIPS 2020

R2 v1 2026-06-23T17:15:49.079Z