AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Fast Optimal Transport through Sliced Generalized Wasserstein Geodesics

Guillaume Mahey, Laetitia Chapel, Gilles Gasso, Clément Bonet, Nicolas Courty

NeurIPS 2023 · Learning theory and algorithms › Optimal transport · approach: Wasserstein barycenters and GW · 0 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 min-SWGG transport map instead of nearest-neighbor correspondence in ICPICP · Point clouds n=500Sinkhorn divergence: 3.54 -> 0.05Improved
Use min-SWGG transport map instead of nearest-neighbor correspondence in ICPICP · Point clouds n=3000Sinkhorn divergence: 96.9 -> 37.6Improved
Use min-SWGG transport map instead of nearest-neighbor correspondence in ICPICP · Point clouds n=150000Sinkhorn divergence: 23.3 -> 6.7Improved
Use min-SWGG instead of exact OT map in ICPICP · Point clouds n=500Sinkhorn divergence: 0.32 -> 0.05Improved
Use min-SWGG instead of exact OT map in ICPICP · Point clouds n=3000Sinkhorn divergence: 48.4 -> 37.6Improved
Use min-SWGG instead of exact OT map in ICPICP · Point clouds n=3000running time (s): 58.46 -> 0.90Improved
Use min-SWGG instead of exact OT map in ICPICP · Point clouds n=500running time (s): 0.18 -> 0.04 is faster; NN is 0.02Hurt
Use min-SWGG instead of NN correspondence in ICPICP · Point clouds n=150000running time (s): 59.37 -> 105.75Hurt
Use min-SWGG when exact OT is infeasibleICP · Point clouds n=150000feasibilityImproved
Optimize projection direction by gradient descent instead of random search (ablation)min-SWGG · Gaussians d=200, n=1000approximation of WDImproved
Optimize projection direction vs random search in low dimension (ablation)min-SWGG · Gaussians d=2approximation of WDNo clear effect
Use gradient-descent min-SWGG vs SW, max-SW, PWD in gradient flowmin-SWGG · Gradient flow d=500, n=100alignment of distributionsImproved

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