AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Bayesian Level Set Clustering

David Buch, Miheer Dewaskar, David B. Dunson

JMLR 2026 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 6 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
tune DBSCAN MinPts from 16 to 60 using simulation ground truthDBSCAN · EDCCI galaxy clustersspecificity: 0.20 -> 0.65Improved
tune DBSCAN MinPts from 16 to 60 using simulation ground truthDBSCAN · Simulated sky surveysensitivity and specificity: performance improved to match that of BALLETImproved
use BALLET instead of DBSCAN with default MinPts=16BALLET · Simulated sky surveyspecificity: 0.49 -> 0.99Improved
use BALLET instead of DBSCAN with default MinPts=16BALLET · Simulated sky surveyexact match: 0.45 -> 0.88Improved
use BALLET instead of DBSCAN with default MinPts=16BALLET · Simulated sky surveysensitivity: 0.86 -> 0.78Hurt
use BALLET instead of DBSCAN with default MinPts=16BALLET · EDCCI galaxy clustersspecificity: 0.20 -> 0.69Improved
use BALLET upper credible bound instead of point estimateBALLET · Simulated sky surveysensitivity: 0.78 -> .89Improved
use BALLET upper credible bound instead of point estimateBALLET · Simulated sky surveyspecificity: 0.99 -> .96Hurt
use BALLET lower credible bound instead of point estimateBALLET · Simulated sky surveysensitivity: 0.78 -> .62Hurt
use decision-theoretic BALLET estimate instead of plugin estimator (ablation)BALLET · EDCCI galaxy clustersexact match: 0.53 -> 0.51No clear effect
vary DBSCAN-style neighbourhood parameter k (ablation)BALLET · Simulated sky surveysensitivity and specificityNo clear effect

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