AI Paper Atlas

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

ICLR 2026 · 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
use exact GPCA instead of tangent PCA on generic random Gaussian covariancesWasserstein 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 orientationWasserstein GPCA · diagonal covariance gridcomponentsNo clear effect
use GPCA instead of TPCA near the boundary of the SPD coneWasserstein GPCA · same-eigenvalue covariances, |a-b|/|a+b| about 0.8componentsMixed
use continuous GPCAgen instead of discrete TPCA on point cloudsGPCAgen · ModelNet40 lamps and chairscomponent qualityImproved
use Wasserstein GPCA instead of PCA on PointNet latent codesGPCAgen · ModelNet40 lamps and chairsinterpretability of componentsImproved
use GPCA scores for outlier detectionGPCAgen · chairs vs cars and planesscore separationImproved

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