atlas

Research map / Learning theory and algorithms / Optimal transport

A Swiss Army Knife for Minimax Optimal Transport

ICML 2020 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 10 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Adding stability-based selection of the cost matrix (choosing the most stable cost)OT cost matrix selection · Color transfer (ocean/sky images)stability of cost matricesHelped
Cutting-set method with constraint dropping (Algorithm 1) versus solving the full LPRobust OT with |C|=10 to 90 cost matrices · m=n=100 syntheticexecution timeHelped
Stability of cost matrix (noise-sensitivity correlation)Cost matrices on toy Gaussian and MNIST-UMAP data · Noise sensitivity experimentnoise sensitivityHelped
Using regularized (entropic) transport in Step 2 instead of exact OT (ablation)Cutting-set algorithm · Synthetic, |C|=40, lambda in {1,0.1,0.01}convergenceNo clear effect
Initializing P0 at a subset of vertices of the transportation polytope in the regularized case (ablation)Cutting-set algorithm with entropic regularization · Synthetic regularized settingconvergenceHurt

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