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
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 PRW instead of SRW distance | PRW · movie scripts Dunkirk vs Gravity | distance: 0.184 -> 0.126 | Mixed |
| use PRW instead of SRW distance | PRW · Shakespeare Henry V vs Romeo and Juliet | distance: 0.311 -> 0.272 | Mixed |
| use PRW with RGAS/RAGAS instead of Frank-Wolfe SRW | PRW · fragmented hypercube d from 25 to 500 | computation time | Improved |
| use adaptive RAGAS instead of RGAS (ablation) | RAGAS · fragmented hypercube, learning rates 0.01 and 0.1 | computation time variance | Improved |
| compare RAGAS with RGAS solution quality (ablation) | RAGAS · fragmented hypercube, n up to 1000 | estimation error | No clear effect |
| use PRW instead of SRW and Wasserstein under moderate to high noise | PRW · fragmented hypercube noise | mean relative error | Improved |
| use PRW instead of SRW at small noise | PRW · fragmented hypercube noise | mean relative error | Improved |
| add white noise N(0, Id) to data | PRW · fragmented hypercube, varying k | normalized PRW distance | No clear effect |
Closest papers by meaning
- Tree-Sliced Wasserstein Distance with Nonlinear Projection (ICML 2025 · similarity 0.87)
- Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants (ICML 2025 · similarity 0.87)
- On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity (ICML 2024 · similarity 0.87)
- Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space (NeurIPS 2025 · similarity 0.87)
- Semidefinite Relaxations of the Gromov-Wasserstein Distance (NeurIPS 2024 · similarity 0.86)
- Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis (ICML 2025 · similarity 0.86)
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.
