AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Meta Optimal Transport

Brandon Amos, Giulia Luise, Samuel Cohen, Ievgen Redko

ICML 2023 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 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
Initialize Sinkhorn with predicted Meta OT dual potentials instead of zero potentialsSinkhorn · MNISTruntime to marginal error 10^{-2}: 4.5\cdot10^{-3} -> 2.3\cdot10^{-3}Improved
Initialize Sinkhorn with predicted Meta OT dual potentials instead of Gaussian initializationSinkhorn · Spherical transportruntime to marginal error 10^{-2}: 0.56 -> 7.8\cdot10^{-2}Improved
Use Meta OT warm starts and 5 Sinkhorn iterations rather than WAR with 20 iterationsWAR classification · Fashion MNIST, 40% label noiseclassification accuracy: 88.08 -> 89.08Improved
Use Meta OT warm starts and 5 Sinkhorn iterations rather than WAR with 20 iterationsWAR classification · Cifar-10, 40% label noiseclassification accuracy: 87.07 -> 83.57Hurt
Use Meta OT warm starts and 5 Sinkhorn iterations rather than WAR with 20 iterationsWAR classification · Cifar-100, 40% label noiseclassification accuracy: 61.63 -> 61.13No clear effect
Replace zero initialization with Meta OT warm starts while using 5 iterationsWAR classification · Fashion MNIST, 0% label noiseclassification accuracy: 94.75 -> 94.70No clear effect
Initialize W2GN from Meta ICNN predictions rather than train from scratchW2GN color transfer · Color transferdual value after 1k iterations: 0.96 -> 1.0Improved
Predict one discrete dual potential and recover the other using the optimality relationMeta OT discrete model · MNIST and spherical transportruntime to convergenceImproved
Use an amortized Meta ICNN initialization before W2GN fine-tuningW2GN color transfer · Color transferconvergence / dual objectiveImproved
Use Meta OT warm starts with 5 iterations instead of zero initialization with 20 iterationsWAR training · Fashion MNISTruntime per epoch: 17.04 -> 14.37Improved

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