Research map / Learning theory and algorithms / Kernels and regression theory
On Sufficient Graphical Models
Bing Li, Kyongwon Kim
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 nonlinear sufficient dimension reduction step (vs Naive conjoined conditional covariance operator) (ablation) | Sufficient graphical model · DREAM 4 Network 1 | AUC: 0.78 -> 0.85 | Improved |
| add nonlinear sufficient dimension reduction step (vs Naive) (ablation) | Sufficient graphical model · DREAM 4 Network 5 | AUC: 0.71 -> 0.79 | Improved |
| add nonlinear sufficient dimension reduction step (vs Naive) (ablation) | Sufficient graphical model · DREAM 4 Network 2 | AUC: 0.76 -> 0.81 | Improved |
| add dimension reduction (vs fully nonparametric methods) in high-dimensional setting p=200 > n | Sufficient graphical model · Simulation Models III and IV (p=200, n=50, 100) | averaged ROC curve | Improved |
| use sufficient graphical model instead of Gaussian or copula Gaussian methods on non-Gaussian data | Sufficient graphical model · Simulation Models I and II | averaged ROC curve | Improved |
| use sufficient graphical model instead of additive conditional independence method | Sufficient graphical model · Simulation Model I (additive) vs Model II (non-additive) | averaged ROC curve | Mixed |
| use sufficient graphical model instead of Gaussian graphical model methods on Gaussian data | Sufficient graphical model · Simulation Model V (Gaussian, p=20) | averaged ROC curve | Hurt |
| use d_ij=2 instead of d_ij=1 for dimension of reduced space (ablation) | Sufficient graphical model · DREAM 4 | AUC | No clear effect |
| use d_ij=1 instead of d_ij=2 for dimension of reduced space (ablation) | Sufficient graphical model · Simulation Models I-II | averaged ROC curve | No clear effect |
| sufficient graphical model vs DREAM 4 champion | Sufficient graphical model · DREAM 4 Network 1 | AUC: 0.91 -> 0.85 | Hurt |
| sufficient graphical model vs DREAM 4 champion | Sufficient graphical model · DREAM 4 Network 5 | AUC: 0.75 -> 0.79 | Improved |
Closest papers by meaning
- A Flexible Framework for Nonparametric Graphical Modeling that Accommodates Machine Learning (ICML 2020 · similarity 0.89)
- Learning general conditional independence structures via the neighbourhood lattice (JMLR 2026 · similarity 0.89)
- Model-Preserving Sensitivity Analysis for Families of Gaussian Distributions (JMLR 2020 · similarity 0.89)
- The Multiple Quantile Graphical Model (NeurIPS 2016 · similarity 0.87)
- Fairness-Aware Estimation of Graphical Models (NeurIPS 2024 · similarity 0.85)
- Learning Local Neighborhoods of Non-Gaussian Graphical Models (AAAI 2025 · similarity 0.85)
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.
