Research map / Probabilistic and scientific modeling / Variational and generative sampling
Parallel Streaming Wasserstein Barycenters
Matthew Staib, Sebastian Claici, Justin M Solomon, Stefanie Jegelka
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed stochastic parallel barycenter algorithm instead of the linear-program baseline | Wasserstein barycenter estimation for the UCI skin segmentation posterior · UCI skin segmentation posterior | W2: 34.3 -> 26.3 | Improved |
| Increase the linear-program mesh from 24 to 40 support points | Linear-program barycenter baseline · UCI skin segmentation posterior | W2: 41.1 -> 59.3 | Hurt |
| Use a streaming estimate while the input distributions drift | Parallel Streaming Wasserstein Barycenters · Drifting von Mises-Fisher distributions on S^2 | barycenter tracking | Improved |
Closest papers by meaning
- Stochastic Wasserstein Barycenters (ICML 2018 · similarity 0.91)
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization (ICML 2025 · similarity 0.88)
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures (NeurIPS 2026 · similarity 0.86)
- Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows (ICML 2025 · similarity 0.86)
- Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport (ICLR 2025 · similarity 0.85)
- Estimating Barycenters of Distributions with Neural Optimal Transport (ICML 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
