Research map / Learning theory and algorithms / Matrix and tensor methods
Estimation of Graphical Models through Structured Norm Minimization
Davoud Ataee Tarzanagh, 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 |
|---|---|---|---|
| use 6 instead of 4 structured matrices in the norm (ablation) | SSONA · Lung cancer gene expression | average classification accuracy: 0.807 -> 0.839 | Improved |
| use 6 instead of 4 structured matrices in the norm (ablation) | SSONA · Lung cancer gene expression | average number of genes selected: 61.44 -> 56.111 | Improved |
| use 7 instead of 5 structured matrices (ablation) | SSONA · 20Newsgroups atheism classification | misclassification rate: 0.435 -> 0.401 | Improved |
| replace group lasso with SSONA (6 matrices), no prior group structure | lung cancer classification · Lung cancer gene expression | average classification accuracy: 0.815 -> 0.839 | No clear effect |
| replace overlapping group lasso with SSONA (7 matrices), no prior group structure | document classification · 20Newsgroups atheism classification | misclassification rate: 0.390 -> 0.401 | No clear effect |
| use SSONA instead of graphical lasso on structured networks | graph estimation · Simulated structured graphical models, p=100, m=100 and 200 | network structure recovery | Improved |
| use SSONA rather than CovSel, HGL, glasso-SF, Pseudo-Exact, PGADM | graph estimation · Synthetic problems (performance profiles) | edges correctly estimated and squared error: solves more than 80 % of the test problems | Improved |
Closest papers by meaning
- Beyond normality: Learning sparse probabilistic graphical models in the non-Gaussian setting (NeurIPS 2017 · similarity 0.88)
- Estimation of Sparse Gaussian Graphical Models with Hidden Clustering Structure (JMLR 2024 · similarity 0.88)
- Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization (NeurIPS 2017 · similarity 0.87)
- Learning to Discover Sparse Graphical Models (ICML 2017 · similarity 0.87)
- Fast structure learning with modular regularization (NeurIPS 2019 · similarity 0.87)
- Breaking the curse of dimensionality in structured density estimation (NeurIPS 2024 · similarity 0.86)
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.
