Research map / Learning theory and algorithms / Matrix and tensor methods
Learning Large-Scale MTP$_2$ Gaussian Graphical Models via Bridge-Block Decomposition
Xiwen Wang, Jiaxi Ying, Daniel P. Palomar
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 |
|---|---|---|---|
| Apply bridge-block decomposition before solving the subproblems | BCD, PGD, PQN-LBFGS, and FPN · Synthetic BA and SBM graphs, p=5000 and p=20000 | computational time to converge: one to four orders of magnitude | Improved |
| Apply bridge-block decomposition before solving the subproblems | BCD, PGD, PQN-LBFGS, and FPN · Crop Image dataset, p=24000 | convergence speed: a minimum of three orders of magnitude | Improved |
| Apply bridge-block decomposition | Existing solvers · Synthetic graphs, p=20000 | ability to solve within 10^4 seconds: 10^4 seconds | Improved |
| Use bridge-block decomposition on a sparser BA graph rather than an SBM graph | BCD · Synthetic BA and SBM graphs | speed-up | Improved |
| Use bridge-block decomposition with a higher-complexity solver | BCD · Synthetic graphs | speed-up | Improved |
| Use bridge-block decomposition with many subgraphs | BCD · Block-tridiagonal community graphs | ratio of improvement in computational time | Improved |
Closest papers by meaning
- Learning Non-Gaussian Graphical Models via Hessian Scores and Triangular Transport (JMLR 2024 · similarity 0.87)
- Learning partial correlation graphs and graphical models by covariance queries (JMLR 2021 · similarity 0.87)
- Beyond normality: Learning sparse probabilistic graphical models in the non-Gaussian setting (NeurIPS 2017 · similarity 0.86)
- Learning Gaussian DAG Models without Condition Number Bounds (ICML 2025 · similarity 0.86)
- Learning to Discover Sparse Graphical Models (ICML 2017 · similarity 0.86)
- Distribution Learning Meets Graph Structure Sampling (NeurIPS 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.
