Research map / Learning theory and algorithms / Optimal transport
Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem
DongDong Ge, Haoyue Wang, Zikai Xiong, Yinyu Ye
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 MAAIPM instead of BADMM | Wasserstein barycenter computation with pre-specified support · Synthetic barycenter problems | computation time | Improved |
| Use MAAIPM instead of IBP with ε=0.1 | Wasserstein barycenter computation with pre-specified support · Synthetic barycenter problems | solution quality | Improved |
| Decrease IBP regularization from ε=0.1 | IBP · Synthetic barycenter problems | computation time | Hurt |
| Use MAAIPM instead of BADMM or IBP | Wasserstein barycenter computation with free support · Synthetic free-support problems | objective value | Improved |
| Update support more frequently and apply jump tricks | MAAIPM · Synthetic free-support problems | objective value | Improved |
| Use SLRM or DLRM instead of the MATLAB solver for Newton equations | Barycenter-structured normal equations · Normal-equation experiments | computation time | Improved |
| Use MAAIPM instead of Gurobi or MOSEK | Wasserstein barycenter computation with pre-specified support · Synthetic barycenter problems | computation time | Improved |
| Use MAAIPM instead of IBP with ε=0.1 | Wasserstein barycenter computation with free support · Synthetic free-support problems | barycenter quality | Improved |
| Use MAAIPM instead of BADMM or IBP | Image Wasserstein barycenter computation · MNIST and Fashion-MNIST | barycenter clarity | Improved |
| Choose DLRM when m² > 4∑ᵗ mₜ² rather than using SLRM | MAAIPM normal-equation solver · Normal-equation experiments | computation time | Mixed |
Closest papers by meaning
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization (ICML 2025 · similarity 0.91)
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures (NeurIPS 2026 · similarity 0.89)
- Estimating Barycenters of Distributions with Neural Optimal Transport (ICML 2024 · similarity 0.87)
- Energy-Guided Continuous Entropic Barycenter Estimation for General Costs (NeurIPS 2024 · similarity 0.87)
- Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows (ICML 2025 · similarity 0.87)
- Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness (ICML 2025 · similarity 0.85)
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.
