Research map / Probabilistic and scientific modeling / Variational and generative sampling
Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models
Subhabrata Majumdar, George Michailidis
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 |
|---|---|---|---|
| Use joint JMMLE rather than separate estimation for regression matrices | Regression matrices across related datasets · Simulation 1, all six dimension/sparsity settings | MCC | Improved |
| Use joint JMMLE rather than separate estimation for regression matrices | Regression matrices across related datasets · Simulation 1, regression matrices (200,200,100), high sparsity | TPR: 0.32(0.01) -> 0.97(0.017) | Improved |
| Use joint JMMLE rather than separate estimation for regression matrices | Regression matrices across related datasets · Simulation 1, regression matrices (30,60,100), low sparsity | RF: 0.18(0.021) -> 0.27(0.024) | Hurt |
| Incorporate upper-layer data using JMMLE rather than estimate the lower-layer network with JSEM alone | Lower-layer precision matrices · Simulation 1, all six settings | RF | Improved |
| Use joint JMMLE rather than separate estimation for lower-layer precision matrices | Lower-layer precision matrices · Simulation 1, low-sparsity settings | TPR | Hurt |
| Use joint JMMLE rather than separate estimation for lower-layer precision matrices | Lower-layer precision matrices · Simulation 1, high-sparsity settings | RF | Improved |
| Increase sample size | JMMLE global and simultaneous testing · Simulation 2, tested settings | power | Improved |
| Increase sample size | JMMLE global and simultaneous testing · Simulation 2, tested settings | FDR | Improved |
| Use JMMLE-based global tests rather than separate estimation | Global hypothesis testing · Simulation 2, settings with high dimensions | size | Improved |
| Use JMMLE-based simultaneous tests rather than separate estimation | Simultaneous hypothesis testing · Simulation 2, settings shown | FDR | Improved |
Closest papers by meaning
- Penalized Maximum Likelihood Estimation of Multi-layered Gaussian Graphical Models (JMLR 2016 · similarity 0.85)
- A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models (ICML 2018 · similarity 0.83)
- Simultaneous Inference for Pairwise Graphical Models with Generalized Score Matching (JMLR 2020 · similarity 0.83)
- Fairness-Aware Estimation of Graphical Models (NeurIPS 2024 · similarity 0.81)
- A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity (ICML 2025 · similarity 0.80)
- Gaussian Graphical Modelling Without Independence Assumptions for Uncentered Data (AAAI 2025 · similarity 0.80)
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.
