Research map / Probabilistic and scientific modeling / Variational and generative sampling
Joint Structural Estimation of Multiple Graphical Models
Jing Ma, George Michailidis
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add thresholding within groups (direction consistency) to JSEM (ablation) | JSEM · Simulation 3 (K=5, p=100) | F1: 0.71 -> 0.83 | Improved |
| add thresholding within groups (direction consistency) to JSEM (ablation) | JSEM · Simulation 3 (K=10, p=40) | F1: 0.78 -> 0.82 | Improved |
| add maximum likelihood refitting step to JSEM (ablation) | JSEM · Simulation 1 | Frobenius norm loss: 0.71 -> 0.25 | Improved |
| add maximum likelihood refitting step to JSEM (ablation) | JSEM · Simulation 1 | SHD: 54 -> 54 | No clear effect |
| add maximum likelihood refitting step to GGL (ablation) | GGL · Simulation 1 | Frobenius norm loss: 0.70 -> 0.29 | Improved |
| increase pattern misspecification rho from 0 to 0.4 (ablation) | JSEM · Simulation 2 | F1: 0.75 -> 0.62 | Hurt |
| increase pattern misspecification rho from 0 to 0.6 (ablation) | JSEM · Simulation 2 | F1: 0.75 -> 0.52 | Hurt |
| joint estimation JSEM instead of separate Glasso | Glasso · Simulation 1 | F1: 0.32 -> 0.73 | Improved |
| joint estimation JSEM instead of separate Glasso at high misspecification (rho=0.6) | Glasso · Simulation 2 | F1: 0.54 -> 0.52 | No clear effect |
| JSEM instead of GGL (known group structure) | GGL · Simulation 2 (rho=0) | F1: 0.52 -> 0.75 | Improved |
Closest papers by meaning
- Robust Estimation of Tree Structured Gaussian Graphical Models (ICML 2019 · similarity 0.89)
- Penalized Maximum Likelihood Estimation of Multi-layered Gaussian Graphical Models (JMLR 2016 · similarity 0.89)
- A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models (ICML 2018 · similarity 0.89)
- High-Dimensional Inference for Cluster-Based Graphical Models (JMLR 2020 · similarity 0.89)
- Bayesian Covariate-Dependent Gaussian Graphical Models with Varying Structure (JMLR 2022 · similarity 0.88)
- Learning Local Neighborhoods of Non-Gaussian Graphical Models (AAAI 2025 · similarity 0.87)
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.
