Research map / Learning theory and algorithms / Optimal transport
A novel notion of barycenter for probability distributions based on optimal weak mass transport
Elsa Cazelles, Felipe Tobar, Joaquin Fontbona
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 |
|---|---|---|---|
| Weak barycenter instead of Wasserstein barycenter | OWT barycenter · 2D Gaussians with outliers (Bernoulli p = 0.05) | robustness to outliers | Improved |
| Weak barycenter instead of Wasserstein barycenter | OWT barycenter · Pair-of-ellipses with outliers | shape preservation | Improved |
| Weak barycenter instead of OT barycenter | OWT barycenter · 2D Gaussians (r = 100, K = 15) | spread of barycenter | Improved |
| Increase entropic regularisation epsilon in OT Sinkhorn barycenter (ablation) | OT Sinkhorn barycenter · 2D Gaussians | closeness to weak barycenter | Mixed |
| Weak barycenter instead of OT barycenter | OWT barycenter · Spiral distributions | shape preservation | Improved |
| OWT plan instead of OT or entropic-OT plan (epsilon = 1) | Algorithm 1 barycenter · MNIST noisy digit 8 | dispersion/shape quality | Improved |
| Weak barycenter streaming procedure instead of fixed-grid Wasserstein barycenter | Algorithm 2 · Flow cytometry (K = 15 patients) | alignment of common features | Improved |
Closest papers by meaning
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization (ICML 2025 · similarity 0.89)
- Energy-Guided Continuous Entropic Barycenter Estimation for General Costs (NeurIPS 2024 · similarity 0.88)
- Estimating Barycenters of Distributions with Neural Optimal Transport (ICML 2024 · similarity 0.87)
- Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows (ICML 2025 · similarity 0.87)
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures (NeurIPS 2026 · similarity 0.86)
- Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport (ICLR 2025 · similarity 0.86)
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.
