AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Learning Latent Variable Models by Pairwise Cluster Comparison: Part II - Algorithm and Evaluation

Nuaman Asbeh, Boaz Lerner

JMLR 2016 · Probabilistic and scientific modeling › Causal discovery · approach: Identifiability with hidden confounders · 4 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 LPCC instead of BPC and EFA for latent structure learningLPCC · Simulated G1-G6, binary and ternarySHDImproved
use LPCC instead of EFA when latents are independent (G1)LPCC · Simulated G1SHDNo clear effect
use LPCC instead of BPC when latents have fewer than four children (G1)LPCC · Simulated G1SHD: BPC SHD=6 (all six edges missed)Improved
increase parametrization level pjEFA · Simulated G2 and G4SHDHurt
increase number of indicators per latentLPCC · Simulated G2, pj=0.75SHD: errs twice when more than 3 indicatorsNo clear effect
initialize LPCC with Citrus clustering and cluster purification instead of SOM (ablation)LPCC · Mass cytometry CyTOFbiological meaningfulness of learned latent model: eight latents, not biologically meaningful -> five latents covering sixteen of 37 markersImproved
change BPC significance level alpha (ablation)BPC · Political action survey and Holzinger-Swinefordlearned model quality: alpha 0.01, 0.05 vs 0.1Mixed

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