Gradient descent algorithms for Bures-Wasserstein barycenters

S Chewi, T Maunu, P Rigollet… - … on Learning Theory, 2020 - proceedings.mlr.press
We study first order methods to compute the barycenter of a probability distribution $ P $
over the space of probability measures with finite second moment. We develop a framework …

On the complexity of approximating multimarginal optimal transport

T Lin, N Ho, M Cuturi, MI Jordan - Journal of Machine Learning Research, 2022 - jmlr.org
We study the complexity of approximating the multimarginal optimal transport (MOT)
distance, a generalization of the classical optimal transport distance, considered here …

Multi-marginal optimal transport and probabilistic graphical models

I Haasler, R Singh, Q Zhang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
We study multi-marginal optimal transport problems from a probabilistic graphical model
perspective. We point out an elegant connection between the two when the underlying cost …

Optimal decentralized distributed algorithms for stochastic convex optimization

E Gorbunov, D Dvinskikh, A Gasnikov - arXiv preprint arXiv:1911.07363, 2019 - arxiv.org
We consider stochastic convex optimization problems with affine constraints and develop
several methods using either primal or dual approach to solve it. In the primal case, we use …

Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent

J Altschuler, S Chewi, PR Gerber… - Advances in Neural …, 2021 - proceedings.neurips.cc
We study first-order optimization algorithms for computing the barycenter of Gaussian
distributions with respect to the optimal transport metric. Although the objective is …

Wasserstein barycenters are NP-hard to compute

JM Altschuler, E Boix-Adsera - SIAM Journal on Mathematics of Data Science, 2022 - SIAM
Computing Wasserstein barycenters (aka optimal transport barycenters) is a fundamental
problem in geometry which has recently attracted considerable attention due to many …

Entropy-regularized 2-Wasserstein distance between Gaussian measures

A Mallasto, A Gerolin, HQ Minh - Information Geometry, 2022 - Springer
Gaussian distributions are plentiful in applications dealing in uncertainty quantification and
diffusivity. They furthermore stand as important special cases for frameworks providing …

Multimarginal optimal transport with a tree-structured cost and the schrodinger bridge problem

I Haasler, A Ringh, Y Chen, J Karlsson - SIAM Journal on Control and …, 2021 - SIAM
The optimal transport problem has recently developed into a powerful framework for various
applications in estimation and control. Many of the recent advances in the theory and …

Fixed-support Wasserstein barycenters: Computational hardness and fast algorithm

T Lin, N Ho, X Chen, M Cuturi… - Advances in neural …, 2020 - proceedings.neurips.cc
We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in
computing the Wasserstein barycenter of $ m $ discrete probability measures supported on …

Computational guarantees for doubly entropic wasserstein barycenters

T Vaskevicius, L Chizat - Advances in Neural Information …, 2024 - proceedings.neurips.cc
We study the computation of doubly regularized Wasserstein barycenters, a recently
introduced family of entropic barycenters governed by inner and outer regularization …