mlsanityData to 14 Oct 2026

Federated Calculation of the Free-Support Transportation Barycenter by Single-Loop Dual Decomposition

arXiv 2507.19627 ↗First posted 25 Jul 2025cs.LG math.OC stat.MLcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose an efficient federated dual decomposition algorithm for calculating the Wasserstein barycenter of several distributions, including choosing the support of the solution. The algorithm does not access local data and uses only highly aggregated information. It also does not require repeated solutions to mass transportation problems. Because of the absence of any matrix-vector operations, the algorithm exhibits a very low complexity of each iteration and significant scalability. We illustrate its virtues and compare it to the state-of-the-art methods on several examples of mixture models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 51 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

24 of 51 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2017Federated Multi-Task Learningcited by 672
  5. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  6. 2017Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcited by 223
  7. 2013Fast Computation of Wasserstein Barycenterscited by 216
  8. 2016Stochastic Optimization for Large-scale Optimal Transportcited by 189
  9. 2023Handbook of Convergence Theorems for (Stochastic) Gradient Methodscited by 163
  10. 2020An Improved Analysis of Stochastic Gradient Descent with Momentumcited by 119
  11. 2018Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithmcited by 112
  12. 2020Fair Regression with Wasserstein Barycenterscited by 100
12 more
  1. 2019A Wasserstein-type distance in the space of Gaussian Mixture Modelscited by 75
  2. 2019On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithmscited by 62
  3. 2017Sliced Wasserstein Distance for Learning Gaussian Mixture Modelscited by 59
  4. 2018A Unified Analysis of Stochastic Momentum Methods for Deep Learningcited by 55
  5. 2017Multilevel Clustering via Wasserstein Meanscited by 49
  6. 2015A Smoothed Dual Approach for Variational Wasserstein Problemscited by 29
  7. 2018Semi-dual Regularized Optimal Transportcited by 26
  8. 2022Fair learning with Wasserstein barycenters for non-decomposable performance measurescited by 24
  9. 2018Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenterscited by 21
  10. 2023An Integrated Transportation Distance Between Kernels and Approximate Dynamic Risk Evaluation in Markov Systemscited by 9
  11. 2020Randomised Wasserstein Barycenter Computation: Resampling with Statistical Guaranteescited by 8
  12. 2023Mitigating Discrimination in Insurance with Wasserstein Barycenterscited by 7

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decodingcited by 9