AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Recursive Nearest Agglomeration (ReNA): Fast Clustering for Approximation of Structured Signals

Andrés Hoyos-Idrobo, Gael P. Varoquaux, Jonas Kahn, Bertrand Thirion

TPAMI 2018 · Learning theory and algorithms › Clustering · approach: Subspace clustering · 18 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
use balanced-cluster feature grouping (Ward, SLIC, ReNA) instead of random projections or downsampling at high reductionlogistic regression · Extended Yale B facesaccuracy: up to 10% betterImproved
use ReNA feature grouping before classifier instead of raw datalogistic regression · OASIS, HCP and other datasetsprediction accuracy: p-value < 10^-4Improved
use ReNA instead of raw datal2 logistic regression · Extended Yale B facesaccuracy: slightly worse than rawHurt
use percolating linkage (single, average, complete) for feature groupinglogistic regression · Extended Yale B facesaccuracy: fail to achieve the same performance as rawHurt
add ICA after ReNA reduction instead of random projections or Nystromspatial ICA · HCP 40 componentsaverage correlation with raw components: greater than 0.74 vs < 0.4Improved
use ReNA reduction before ICAspatial ICA · HCP 93 subjectscomputation time: 16 times faster than rawImproved
use ReNA reduction before ICAspatial ICA · HCP 93 subjectstotal analysis time: factor of 15Improved
use Ward instead of ReNA for approximationfeature grouping · k = p/20approximation fidelity and time: slightly better approximations but slowerMixed
downsample images before ICA instead of raw dataspatial ICA · HCP across two sessionscomponent consistency: more consistent than raw dataImproved

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