Research map / Learning theory and algorithms / Optimal transport
Debiased Sinkhorn barycenters
Hicham Janati, Marco Cuturi, Alexandre Gramfort
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 Lebesgue reference measure instead of the Sinkhorn divergence | Gaussian barycenters · Univariate Gaussian barycenters | barycenter variance | Hurt |
| Use the product reference measure instead of the Sinkhorn divergence | Gaussian barycenters · Univariate Gaussian barycenters | barycenter variance | Hurt |
| Use the debiased Sinkhorn divergence | Gaussian barycenters · Univariate Gaussian barycenters | barycenter variance | Improved |
| Use the debiased Sinkhorn divergence instead of entropic OT with a uniform reference | Barycentric embeddings · MNIST | cross-validation accuracy | Improved |
| Use the debiased Sinkhorn barycenter instead of the uniform-reference entropic OT barycenter | Barycenters of nested ellipses · 10 randomly generated nested ellipses | blurring | Improved |
| Use the debiased Sinkhorn barycenter instead of the uniform-reference entropic OT barycenter | Barycentric interpolation · 3D shape interpolation | edge sharpness | Improved |
| Use the debiased Sinkhorn algorithm instead of IBP | Fixed-support barycenter computation · Univariate Gaussian barycenters | runtime | No clear effect |
Closest papers by meaning
- Faster Wasserstein Distance Estimation with the Sinkhorn Divergence (NeurIPS 2020 · similarity 0.91)
- Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance (NeurIPS 2018 · similarity 0.91)
- Accelerating Sinkhorn algorithm with sparse Newton iterations (ICLR 2024 · similarity 0.89)
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization (ICML 2025 · similarity 0.87)
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures (NeurIPS 2026 · similarity 0.87)
- Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport (NeurIPS 2024 · similarity 0.87)
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.
