AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Contamination-source based K-sample clustering

Xavier Milhaud, Denys Pommeret, Yahia Salhi, Pierre Vandekerkhove

JMLR 2024 · Learning theory and algorithms › Clustering · approach: k-means++ seeding analysis · 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 data-driven tuning of gamma and C (ablation)KCMC k-sample test · Alternative, k=10 config C, n~400empirical power (%): 2 -> 63Improved
add data-driven tuning of gamma and C (ablation)KCMC k-sample test · Alternative, k=10 config C, n~1000empirical power (%): 1 -> 99Improved
add data-driven tuning of gamma and C (ablation)KCMC k-sample test · Alternative, k=7, n~1000empirical power (%): 1 -> 95Improved
add data-driven tuning of gamma and C (ablation)KCMC k-sample test · Alternative, k=4, n~1000empirical power (%): 18 -> 50Improved
add data-driven tuning of gamma and C (ablation)KCMC k-sample test · Alternative, k=4, n~3000empirical power (%): 12 -> 99Improved
increase sample size from about 400 to about 3000KCMC k-sample test (tuned) · Alternative, k=4empirical power (%): 20 -> 50 -> 99Improved
tune penalty and test with epsilon=0.87 fixed instead (ablation)KCMC k-sample test · Null, empirical levelempirical level (%)No clear effect
lower fixed penalty exponent epsilon to much smaller valuesKCMC k-sample test · Null, finite samplesempirical levelHurt
increase number of populations k from 2 to 10KCMC k-sample test · Null, n~400empirical level (%): 5 -> 5No clear effect
reduce n_i p_i below about 50KCMC k-sample test · Null levelempirical levelHurt
increase sample size from about 300 to about 800KCMC clustering · Simulated clustering, K=10clustering accuracy: n≈300 -> n≈800Improved
replace KMBD k-means with KCMC at larger nKCMC clustering · Simulated clustering, n≈1500clustering accuracyImproved

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