AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Exponential Family Graphical Models: Correlated Replicates and Unmeasured Confounders, with Applications to fMRI Data

Yanxin Jin, Yang Ning, Kean Ming Tan

JMLR 2025 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation

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 modelling of unmeasured confounders (vs gamma=1e6) (ablation)proposed method · ADHD-200 fMRI (children)extra edges vs proposal: 80 extra edges when ignoring confounders (children), 65 (adolescent)Improved
add modelling of correlated replicates (vs beta=1e6) (ablation)proposed method · ADHD-200 fMRI (adolescent)extra edges vs proposal: 0 -> 14 extra edges when ignoring correlation (adolescent); 0 for childrenImproved
add both confounder and replicate modelling (vs Meinshausen and Buhlmann)proposed method · ADHD-200 fMRIedges missing vs proposal: 21 and 20 missing edges (children, adolescent)Improved
model correlated replicates and unmeasured confounders jointlyproposed method · Simulated Gaussian graphical model (correlated replicates + confounders)AUC of ROC: all existing methods have area under the curves of approximately 0.5Improved
model piecewise constant confounders (vs Tan et al. 2016)proposed method · Simulation, independent replicates, piecewise constant confounderstrue/false positive rateImproved
model constant confounders with independent replicatesproposed method · Simulation, independent replicates, constant confounderstrue/false positive rateNo clear effect
model correlated replicates (vs independence assumption)proposed method · Simulation, correlated replicates, no confounderstrue/false positive rateImproved

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