AI Paper Atlas

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

NeurIPS 2021 · Learning theory and algorithms › Optimal transport · approach: Sinkhorn and entropic OT algorithms · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Weak barycenter instead of Wasserstein barycenterOWT barycenter · 2D Gaussians with outliers (Bernoulli p = 0.05)robustness to outliersImproved
Weak barycenter instead of Wasserstein barycenterOWT barycenter · Pair-of-ellipses with outliersshape preservationImproved
Weak barycenter instead of OT barycenterOWT barycenter · 2D Gaussians (r = 100, K = 15)spread of barycenterImproved
Increase entropic regularisation epsilon in OT Sinkhorn barycenter (ablation)OT Sinkhorn barycenter · 2D Gaussianscloseness to weak barycenterMixed
Weak barycenter instead of OT barycenterOWT barycenter · Spiral distributionsshape preservationImproved
OWT plan instead of OT or entropic-OT plan (epsilon = 1)Algorithm 1 barycenter · MNIST noisy digit 8dispersion/shape qualityImproved
Weak barycenter streaming procedure instead of fixed-grid Wasserstein barycenterAlgorithm 2 · Flow cytometry (K = 15 patients)alignment of common featuresImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy