AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Learning Gaussian DAGs from Network Data

Hangjian Li, Oscar Hernan Madrid Padilla, Qing Zhou

JMLR 2024 · Probabilistic and scientific modeling › Causal discovery · approach: Differentiable and score-based DAG learning

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
model sample correlation jointly via BCD instead of assuming independent samplesDAG estimation with known ordering · Simulated equi-cor, n<pSHD: 523.0 -> 514.2Improved
model sample correlation jointly via BCD instead of assuming independent samplesDAG estimation with known ordering · Simulated toeplitz, n<pSHD: 599.9 -> 347.8Improved
model sample correlation jointly via BCD instead of assuming independent samplesDAG estimation with known ordering · Simulated toeplitz, n>pSHD: 176.3 -> 80.5Improved
model sample correlation jointly via BCD instead of assuming independent samplesDAG estimation with known ordering · Simulated equi-cor, n>pSHD: 147.6 -> 93.2Improved
use BCD with L1 on DAG instead of KGLassoDAG estimation with known ordering · Simulated equi-cor, n<pSHD: 1166.0 -> 514.2Improved
use BCD instead of KGLassoDAG estimation with known ordering · Simulated AR(5), n>pSHD: 102.4 -> 90.3Improved
use BCD instead of KGLassoDAG estimation with known ordering · Simulated SBM, n>pSHD: 251.0 -> 84.5Improved
increase lambda_p from 0.01/p to 0.1 in graphical Lasso step when n>pBCD · Simulated n>p ROC/AUCAUCImproved
use one-iteration estimate Theta^(1) instead of converged Theta^(infinity)BCD · Simulated ordered DAG, Theta estimationerr(Theta)No clear effect
model sample correlation via BCDDAG estimation with known ordering · Andes+facebook real network, n=500SHD: 235.9 -> 218.6Improved
model sample correlation via BCDDAG estimation with known ordering · Hepar2+celegans_n306, n=100SHD: 357.9 -> 343.7Improved
model sample correlation via BCD with non-block-diagonal ThetaDAG estimation with known ordering · Andes+facebook general Theta, n=100SHD: 398.6 -> 387.9Improved

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