Research map / Learning theory and algorithms / Combinatorial and search optimization
A Screening Rule for l1-Regularized Ising Model Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 exact screening rule (blockwise identification) before node-wise logistic regression | Node-wise logistic regression · synthetic networks, pathwise optimization | runtime | Helped |
| apply screening rule before pseudolikelihood | Pseudolikelihood · synthetic networks, pathwise optimization | runtime and memory footprint | Helped |
| apply screening rule before node-wise logistic regression | Node-wise logistic regression · synthetic networks, model selection (StARS) | runtime: roughly 2x speedup | Helped |
| apply screening rule before node-wise logistic regression | Node-wise logistic regression · lung squamous cell carcinoma mutation data | runtime: roughly 20% faster | Helped |
| apply screening rule before node-wise logistic regression | Node-wise logistic regression · synthetic networks, model selection | edge recovery AUC | No clear effect |
| apply screening rule before pseudolikelihood with PL regularization set to 2λ from NW selection (ablation) | Pseudolikelihood · synthetic networks, model selection | edge recovery AUC | Helped |
| apply screening rule before pseudolikelihood with default model-selected parameter (ablation) | Pseudolikelihood · synthetic networks, model selection | edge recovery AUC | Hurt |
| apply screening rule to inexact NW/PL methods instead of exact problem | Node-wise logistic regression and pseudolikelihood · theory | blockwise structure recovery | Hurt |
| extend screening rule to Ising models with unary potentials (replace criterion with centered moments) | Ising model with unary potentials · theory (Section 6) | blockwise structure recovery | No clear effect |
Closest papers by meaning
- Ising Model Selection Using $\ell_{1}$-Regularized Linear Regression: A Statistical Mechanics Analysis (NeurIPS 2021 · similarity 0.90)
- Interaction Screening: Efficient and Sample-Optimal Learning of Ising Models (NeurIPS 2016 · similarity 0.88)
- Transfer Learning in High-dimensional Ising Models (ICML 2026 · similarity 0.87)
- Generalized Direct Change Estimation in Ising Model Structure (ICML 2016 · similarity 0.87)
- Sample-Efficient L0-L2 Constrained Structure Learning of Sparse Ising Models (AAAI 2021 · similarity 0.86)
- Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample (ICLR 2026 · 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.