Research map / Learning theory and algorithms / Optimal transport
On the Wasserstein Geodesic Principal Component Analysis of probability measures
Nina Vesseron, Elsa Cazelles, Alice Le Brigant, Klein
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 exact GPCA instead of tangent PCA on generic random Gaussian covariances | Wasserstein GPCA · random 2x2 covariance matrices (n=50, 100 trials) | objective: reduces objective by less than 1% | No clear effect |
| use GPCA instead of TPCA on covariances with same orientation | Wasserstein GPCA · diagonal covariance grid | components | No clear effect |
| use GPCA instead of TPCA near the boundary of the SPD cone | Wasserstein GPCA · same-eigenvalue covariances, |a-b|/|a+b| about 0.8 | components | Mixed |
| use continuous GPCAgen instead of discrete TPCA on point clouds | GPCAgen · ModelNet40 lamps and chairs | component quality | Improved |
| use Wasserstein GPCA instead of PCA on PointNet latent codes | GPCAgen · ModelNet40 lamps and chairs | interpretability of components | Improved |
| use GPCA scores for outlier detection | GPCAgen · chairs vs cars and planes | score separation | Improved |
Closest papers by meaning
- Tangential Wasserstein Projections (JMLR 2024 · similarity 0.87)
- Fast PCA in 1-D Wasserstein Spaces via B-splines Representation and Metric Projection (AAAI 2021 · similarity 0.86)
- Fun with Flags: Robust Principal Directions via Flag Manifolds (CVPR 2024 · similarity 0.85)
- A Geometric Analysis of PCA (NeurIPS 2025 · similarity 0.84)
- Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models (NeurIPS 2026 · similarity 0.83)
- Probabilistic Geometric Principal Component Analysis with application to neural data (ICLR 2025 · similarity 0.83)
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.
