AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Projection Robust Wasserstein Distance and Riemannian Optimization

Tianyi Lin, Chenyou Fan, Nhat Ho, Marco Cuturi, Michael I. Jordan

NeurIPS 2020 · Learning theory and algorithms › Optimal transport · approach: Sliced Wasserstein variants · 5 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
use PRW instead of SRW distancePRW · movie scripts Dunkirk vs Gravitydistance: 0.184 -> 0.126Mixed
use PRW instead of SRW distancePRW · Shakespeare Henry V vs Romeo and Julietdistance: 0.311 -> 0.272Mixed
use PRW with RGAS/RAGAS instead of Frank-Wolfe SRWPRW · fragmented hypercube d from 25 to 500computation timeImproved
use adaptive RAGAS instead of RGAS (ablation)RAGAS · fragmented hypercube, learning rates 0.01 and 0.1computation time varianceImproved
compare RAGAS with RGAS solution quality (ablation)RAGAS · fragmented hypercube, n up to 1000estimation errorNo clear effect
use PRW instead of SRW and Wasserstein under moderate to high noisePRW · fragmented hypercube noisemean relative errorImproved
use PRW instead of SRW at small noisePRW · fragmented hypercube noisemean relative errorImproved
add white noise N(0, Id) to dataPRW · fragmented hypercube, varying knormalized PRW distanceNo clear effect

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