AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin

ICML 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 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
add unpaired samples to the paired-only likelihood objective (ablation)EBiEOT-GMM · Weather prediction (90 paired)test log-likelihood: 6.5 -> 20.5Improved
use EBiEOT-GMM instead of naive semi-supervised likelihood baselinesCondNF (SS) / CGMM (SS) · Weather prediction (90 paired, 500 unpaired)test log-likelihood: 0.52 -> 20.5 (vs CondNF (SS)); 0.32 -> 20.5 (vs CGMM (SS))Improved
add unpaired data to CondNF (semi-supervised variant) (ablation)CondNF · Gaussian to Swiss Rollconditional distribution recoveryNo clear effect
semi-supervised CGMM trained with the combined objectiveCGMM (SS) · Gaussian to Swiss Rollconditional distribution recoveryHurt
heuristic key-point guided objectives (OTCS, FSBM) vs EBiEOT likelihoodOTCS, FSBM · Gaussian to Swiss Rollbi-modal conditional recoveryHurt
replace FSBM with EBiEOT in ALAE latent spaceFSBM · Woman-to-Man translationFID: 10.2 -> 9.3Improved
replace FSBM with EBiEOT in ALAE latent spaceFSBM · Old-to-Young translationFID: 11.5 -> 9.4Improved
replace FSBM with EBiEOT trainingFSBM · Woman-to-Man translationtraining time: 5 hours -> 3 minutes on A100Improved
use fully neural parameterization (EBiEOT-NN) instead of Gaussian mixture parameterization (ablation)EBiEOT · Gaussian to Swiss Rolltraining stabilityHurt
increase paired samples from 128 to 16k for EBiEOT-NN (ablation)EBiEOT-NN · Gaussian to Swiss Rollfit to target distributionImproved
increase paired colored-MNIST pairs from 10 to 200 (ablation)EBiEOT-NN · Colored MNIST hue shifttranslation qualityImproved
deterministic-map methods (GNOT, DCPEME, parOT) on multimodal conditionalsGNOT, DCPEME, parOT · Gaussian to Swiss Rollconditional recoveryHurt

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