Wasserstein Barycenters

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 9

All topics

Towards Universal Wasserstein Barycenters through Flow Matching
Sep 29, 2026Eduardo Fernandes MontesumaWasserstein Barycenters Optimal Transport
Sigma Nova Paris, France
Binding Multiple Modalities via Multimodal Wasserstein Barycenter
Sep 27, 2026Xiaole Tang, Jiayi Xu, Xiang Gu +2Cross-Modal Alignment Multimodal Embedding
Xi’an Jiaotong University
SWB-DM: A Calibrated Sliced-Wasserstein-Barycenter Aggregator with Delayed-Momentum Caching for Byzantine-Robust Federated Learning under Partial Participation
Sep 14, 2026Saranraj S, Saranya M S, Alex David S +1Federated Learning Aggregation Byzantine-Robust Federated Learning
Department of AIML Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai, India · Assistant Professor, Department of AIML Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai, India · Professor, Department of AIML Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai, India
A Sub-4 Approximation for Fair $k$ -Means
Sep 7, 2026Kangke Cheng, Guanlin Mo, Shihong Song +1Clustering Group Fairness
University of Science and Technology of China, Hefei, China · School of Informatics, University of Edinburgh, Edinburgh, UK
Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size
Sep 3, 2026A. AfhamRiemannian Optimization Optimization Convergence Analysis
Centre for Quantum Technologies, National University of Singapore, Singapore
Wasserstein Policy Learning for Distributional Outcomes
Jun 17, 2026Yiyan Huang, Cheuk Hang Leung, Qi Wu +1Offline RL Wasserstein Barycenters
School of Statistics and Data Science & Institute of Big Data Research, Shanghai University of Finance and Economics, Shanghai, China
DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation
May 5, 2026Rebecca Clain, Eduardo Fernandes Montesuma, Fred Ngole MboulaMulti-Source Domain Adaptation Domain Adaptation
Universit´e Paris-Saclay, CEA, List, F-91120 Palaiseau, France · Sigma Nova
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
Apr 24, 2026Younes Essafouri, Laure Raynaud, Luciano Drozda +1Gradient-Based Attribution Neural Network Interpretability
Univ. Toulouse, INSA Toulouse, CNRS UMR 5219, IMT, Toulouse, France · Météo-France, CNRS, Univ. Toulouse, CNRM, Toulouse, France · Cerfacs, CNRS/Cerfacs/IRD, CECI, Toulouse, France
Multi-Source Wasserstein Distributionally Robust Graph Learning
Date pendingChuansen Peng, Yifan Xia, Jinshan Zhong +1Graph Structure Learning Graph Representation Learning
School of Mathematics, Sichuan University, Chengdu, Sichuan, 610064, China · School of Statistics and Data Science, Southwestern University of Finance and Economics, Chengdu, Sichuan, 611130, China

Sep 29, 2026, cs.LGJ/K move · Enter open · S save

Towards Universal Wasserstein Barycenters through Flow Matching

Eduardo Fernandes Montesuma

Sigma Nova Paris, France

Wasserstein Barycenters Optimal Transport Wasserstein Distance

Open paper AskPDF arXiv

Defining a weighted mean over probability measures under probability metrics is a central tool in probabilistic machine learning. Under the Wasserstein metric, these are called \emph{Wasserstein barycenters}. While most approaches compute barycenters for a fixed weight vector, approximating the whole family of barycenters over the simplex, which we call the \emph{Wasserstein simplex}, remains underexplored. We refer to this problem as \emph{Universal Barycenter Approximation}, and propose \texttt{BaryFM}, a flow matching model transporting the marginal measures into any barycenter in the Wasserstein simplex. Once trained, the network can draw samples from measures in the Wasserstein simplex through an ordinary differential equation. We validate our method on 4 downstream tasks: domain adaptation, generalization, Bayesian posterior aggregation and algorithmic fairness. \texttt{BaryFM} achieves the best average rank among 15 competing methods across 10 domain adaptation benchmarks, matching or surpassing non-universal solvers.

Momentum

Related topics

Latest papers 9