AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Skewness-Robust Causal Discovery in Location-Scale Noise Models

Daniel Klippert, Alexander Marx

ICML 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Constraint-based structure learning with latents · 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 independence testing instead of likelihood scoringSkewD · 13 established benchmarksmean accuracy (%): 77.43 -> 85.02Improved
use independence testing instead of likelihood scoringLOCI · 13 established benchmarksmean accuracy (%): 77.08 -> 84.09Improved
model skew-normal noise instead of Gaussian noise (SkewD-LL vs LOCI-LL)likelihood scoring · 13 established benchmarksmean accuracy (%): 77.08 -> 77.43No clear effect
model skew-normal noise instead of Gaussian noise (SkewD-IT vs LOCI-IT)independence testing · 13 established benchmarksmean accuracy (%): 84.09 -> 85.02Improved
use SkewD-IT instead of ROCHEcause-effect inference · 13 established benchmarksmean accuracy (%): 87.69 -> 85.02Hurt
increase noise skewness to LSs(1.750)ROCHE · LSs skew-noise datasetsaccuracy: dropping to 81%Hurt
increase noise skewness across the three levelsCAREFL · skew-noise LSNM datasetsaccuracy: 0.90, 0.71, 0.66Hurt
use oracle MEC instead of PC-estimated MEC (ablation)SkewD-MV · synthetic LSNM graphs d=6SHD: 2.27 -> 0.14Improved
use oracle MEC instead of PC-estimated MEC (ablation)SkewD-MV · synthetic LSNM graphs d=10SHD: 4.72 -> 0.04Improved
use SkewD-MV instead of HOSTcausal discovery · synthetic LSNM graphs d=10SHD: 21.21 -> 4.72Improved
use SkewD-MV instead of CAM (SID)causal discovery · synthetic LSNM graphs d=6SID: 9.23 -> 4.35Improved
use SkewD-LL instead of next best methodcause-effect inference · SIMGaccuracy: 88% accuracy, at least 5% above all othersImproved

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