atlas

Research map / Learning theory and algorithms / Optimal transport

Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps

ICML 2023 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 1 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
Use STVS instead of the ℓ1 regularizerGeneralized entropic transport maps · Synthetic constant sparsity-pattern taskNMSEHelped
Use sparsity-inducing elastic costs instead of the squared-ℓ2 costGeneralized entropic transport maps · Synthetic input-dependent sparsity-pattern taskNMSE scaling with dimensionHelped
Increase sparsity of the displacement mapsElastic-ℓ1 transport maps · Single-cell perturbation dataℓ₂²-Sinkhorn divergence in PCA spaceNo clear effect
Induce sparsity in displacementsElastic-ℓ1 transport maps · Single-cell perturbation data, low drug dosagesR² on marker genesHelped
Induce sparsity in displacementsElastic-ℓ1 transport maps · Single-cell perturbation data, high drug dosagesR² on marker genesMixed
Use sparse maps to select marker genesGeneralized entropic transport maps · Single-cell perturbation dataRanked biased overlapHelped

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