AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Learning to Match via Inverse Optimal Transport

Ruilin Li, Xiaojing Ye, Haomin Zhou, Hongyuan Zha

JMLR 2019 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 23 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
add marginal relaxation via regularized Wasserstein distance (RIOT vs IOT) under noiseInverse optimal transport · Synthetic data, sigma=8e-3KL to ground truth plan: 0.1476 -> 0.1365Improved
add marginal relaxation (RIOT vs IOT) for learning cost matrixInverse optimal transport · Synthetic data, sigma=0.08distance to true cost matrix: 8.4623 -> 4.7075Improved
set relaxation parameter too large (delta = 0.05) (ablation)RIOT · Synthetic data, small noiserecovery KLHurt
tune relaxation parameter carefully (delta = 0.01, 0.001) (ablation)RIOT · Synthetic data, small noiserecovery KLImproved
use RIOT instead of itemKNNMatching recommendation · Marriage (DHS)RMSE (x1e-4): 2.4 -> 2.3Improved
use RIOT instead of factorization machineMatching recommendation · Marriage (DHS)MAE (x1e-4): 2.8 -> 1.5Improved

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