AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport

Harry Amad, Mihaela van der Schaar

ICLR 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 learned potential term U (dense traversal bias) (ablation)CLOT with learned metric · Semicircle CTINLL: 23.008 -> -0.662Improved
add learned potential term U to identity metric (ablation)CLOT K_I · Semicircle CTINLL: 105.713 -> -0.532Improved
add learned metric G to the potential-only model (ablation)CLOT K_I - U · Semicircle CTINLL: -0.532 -> -0.662Improved
add learned metric G (least-action bias) to identity model (ablation)CLOT K_I · Semicircle CTICD: 0.323 -> 0.158Improved
add learned potential term U (ablation)CLOT K_theta · Reacheraverage reward: -6.158 -> -6.093Improved
add learned metric G to potential-only model (ablation)CLOT K_I - U · Reacheraverage reward: -6.397 -> -6.093Improved
add learned potential term U (ablation)CLOT K_theta · Cancer_nlaverage reward: 54.44 -> 91.94Improved
add learned metric G to potential-only model (ablation)CLOT K_I - U · Cancer_nlaverage reward: 86.21 -> 91.94Improved
add learned potential term U (ablation)CLOT K_theta · Two moons dropoutWasserstein distance: 0.404 -> 0.079Improved
add learned metric G to potential-only model (ablation)CLOT K_I - U · Two moons dropoutWasserstein distance: 0.060 -> 0.079Hurt
learn eigenvalues E_theta instead of fixed eigenvalues (ablation)CLOT metric G · Semicircle CTINLL: -0.602 -> -0.662Improved
learn eigenvalues E_theta instead of fixed eigenvalues (ablation)CLOT metric G · Canceraverage reward: 98.72 -> 102.49Improved

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