AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities

Hugues Van Assel, Titouan Vayer, Rémi Flamary, Nicolas Courty

NeurIPS 2023 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport

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
use symmetric entropic affinity P^se instead of projected entropic affinity P^espectral clustering · CuMiDa ThroatARI x100: 11.8 -> 44.2Improved
use symmetric entropic affinity P^se instead of P^espectral clustering · SNAREseqARI x100: 55.4 -> 96.6Improved
use P^se instead of P^espectral clustering · CuMiDa Colorectal (2nd listed)ARI x100: 94.0 -> 79.3Hurt
use P^se instead of P^espectral clustering · 12 genomics datasetsARI: 8 out of 12Mixed
use P^se instead of self-tuning P^stspectral clustering · scGEMARI x100: 74.8 -> 71.6Hurt
use t-SNEkhorn instead of t-SNEDR on COIL · COILsilhouette x100: 30.7 -> 52.3Improved
use t-SNEkhorn instead of t-SNEDR on UMNIST · UMNISTsilhouette x100: -0.2 -> 25.4Improved
use t-SNEkhorn instead of t-SNEDR on SNAREseq · SNAREseqsilhouette x100: 35.8 -> 67.9Improved
use t-SNEkhorn instead of t-SNE and UMAPDR on 16 datasets · 16 datasetssilhouette: 15 of 16 datasetsImproved
use t-SNEkhorn instead of t-SNE and UMAPDR on 16 datasets · 16 datasetstrustworthiness: 12 of 16 datasetsMixed
use t-SNEkhorn instead of t-SNEDR on CuMiDa Prostate · CuMiDa Prostatetrustworthiness x100: 80.6 -> 73.1Hurt
use symmetric entropic affinity instead of projected entropic affinity under heteroscedastic noiseaffinity · synthetic multinomial toy datacluster separationImproved

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