AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Multiscale Strategies for Computing Optimal Transport

Samuel Gerber, Mauro Maggioni

JMLR 2017 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 27 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 multiscale transport coordinates instead of single-scale (ablation)OT distance embedding · OASIS MMSER^2: 0.17 -> 0.30Improved
use multiscale instead of single-scale transport (ablation)OT distance embedding · OASIS ageR^2: 0.78 -> 0.82Improved
use multiscale OT instead of LDDMMOT distance embedding · OASIS MMSER^2: 0.18 -> 0.30Improved
use multiscale OT instead of LDDMMOT distance embedding · OASIS CDRR^2: 0.36 -> 0.38Improved
add refinement (neighborhood radius factor above 1) to capacity propagation (ablation)multiscale OT · ellipse and Caffarelli, 5000 pointsrelative errorNo clear effect
add iterated capacity propagation instead of simple propagation (ablation)multiscale OT · ellipse and Caffarelli, 5000 pointsrelative error: errors under one percentImproved
combine potential refinement with capacity propagation (ablation)multiscale OT · ellipse and Caffarelli, 5000 pointsrelative error and timeImproved
use multiscale instead of network simplex or Sinkhornmultiscale OT · ellipse, growing point countcomputation time: memory limit around 2·10^4 constraints vs 2·10^6 constraintsImproved
reduce Sinkhorn tolerance from 1e-5 to 1e-2 (ablation)Sinkhorn · ellipse, growing point countcomputation time: approximately 10% speedupNo clear effect
use potential refinement when transport distance is large relative to supportmultiscale OT · uniform squaresrelative errorHurt

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