AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Near-Optimal Comparison Based Clustering

Michaël Perrot, Pascal Esser, Debarghya Ghoshdastidar

NeurIPS 2020 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 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
use the proposed comparison-based similarity instead of existing multiplicative kernels, measured by comparisons needed for exact planted-cluster recoverySDP clustering with proposed triplet/quadruplet similarities · Simulated planted clusters (n=1000, k=4)comparisons needed for exact recovery (ARI): n(ln n)^4.5 and n(ln n)^5.5 -> n(ln n)^3Improved
use proposed triplet similarity instead of baseline kernel under high crowd noiseSDP clustering with proposed triplet similarity · Simulated planted clusters, n(ln n)^4 comparisonsARI exact recovery vs noise level epsilon: epsilon > 0.9 -> epsilon as small as 0.25Improved
change inner/outer similarity distributions to Uniform+Beta or Uniform+Normal (ablation)Proposed triplet similarity · Simulated planted clustersARIMixed
compare proposed triplet similarity with quadruplet similaritySDP clustering with comparison-based similarities · Simulated planted clustersARINo clear effect
reduce triplet budget on MNIST 1vs.7 from n(ln n)^3 to n(ln n)^2Proposed triplet similarity vs baseline kernel · MNIST 1vs.7 (n=2163)ARI: n(ln n)^3 -> n(ln n)^2Improved
use SPUR-estimated number of clusters instead of known k (ablation)Proposed triplet similarity · MNIST 1vs.7ARINo clear effect
use SPUR-estimated k instead of known k at low triplet budget (ablation)Proposed triplet similarity · MNIST 10 (n=2000), n(ln n)^2 tripletsARIHurt
increase triplets from n(ln n)^2 to n(ln n)^4 (ablation)Proposed triplet similarity with SPUR · MNIST 10estimated number of clusters / ARI: 3 -> 9Improved
use ordinal methods at n(ln n)^4 triplets versus k-means on original dataAll ordinal methods · MNIST 10ARINo clear effect
set k=3 rather than SPUR-estimated k=2 (ablation)Proposed triplet similarity · Car dataset (12112 triplets)ARI agreement with true labels: k=2 -> k=3Improved

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