AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Projection Robust Wasserstein Barycenters

Minhui Huang, Shiqian Ma, Lifeng Lai

ICML 2021 · Learning theory and algorithms › Optimal transport · approach: Wasserstein barycenters and GW · 4 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
Replace WB with RPRWB in D2 clusteringD2 clustering · Reuters SubsetAMI: 0.4200 -> 0.4713Improved
Replace WB with RPRWB in D2 clusteringD2 clustering · BBCnews AbstractAMI: 0.6095 -> 0.6557Improved
Replace WB with RPRWB in D2 clusteringD2 clustering · BBCsport AbstractAMI: 0.6510 -> 0.6892Improved
Replace WB with RPRWB in D2 clusteringD2 clustering · Reuters Subsetclustering iterations: 24.2 -> 23.2Improved
Replace WB with RPRWB in D2 clusteringD2 clustering · BBCnews Abstractclustering iterations: 23.8 -> 22.4Improved
Replace WB with RPRWB in D2 clusteringD2 clustering · BBCsport Abstractclustering iterations: 29.8 -> 14.4Improved
Use RBCD instead of RGA-IBPRPRWB optimization · synthetic computational-time comparisoncomputational timeImproved
Use RPRWB instead of WBbarycenter estimation · synthetic noisy Gaussian distributionsrelative error under noiseImproved
Use RPRWB instead of WBbarycenter estimation · sampled Gaussian distributionsMean Estimation ErrorImproved

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