Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Planar Ising Models
Jason K. Johnson, Diane Oyen, Michael Chertkov, Praneeth Netrapalli
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 |
|---|---|---|---|
| stop planar greedy at the true edge count (Planar oracle) versus learning the maximal planar graph (ablation) | greedy planar Ising learning · Synthetic grid and outer-planar Ising | test likelihood | No clear effect |
| add edges up to the maximal planar graph (ablation) | greedy planar Ising learning · Synthetic Ising, 100 samples | out-of-sample likelihood | Mixed |
| use planar learning instead of UGM pseudo-likelihood tuned | 7x7 grid Ising, small sample sizes · Synthetic 7x7 grid | test likelihood | Improved |
| use planar learning instead of UGM loopy tuned at large sample sizes | synthetic Ising models · Synthetic Ising, large samples | test likelihood | Improved |
| use planar model instead of sparse UGM with 318 edges | Senate voting data · Senate voting 10-fold CV | held-out likelihood | Improved |
| use dense UGM loopy instead of planar model | Senate voting data · Senate voting 10-fold CV | held-out likelihood | Hurt |
Closest papers by meaning
- Inference and Sampling of $K_33$-free Ising Models (ICML 2019 · similarity 0.87)
- Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model (ICML 2020 · similarity 0.86)
- Ising Model Selection Using $\ell_{1}$-Regularized Linear Regression: A Statistical Mechanics Analysis (NeurIPS 2021 · similarity 0.86)
- Predictive Learning on Hidden Tree-Structured Ising Models (JMLR 2021 · similarity 0.86)
- Distribution Learning Meets Graph Structure Sampling (NeurIPS 2025 · similarity 0.85)
- Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models (NeurIPS 2026 · similarity 0.84)
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.
