Research map / Learning theory and algorithms / Sample complexity
Interaction Screening: Efficient and Sample-Optimal Learning of Ising Models
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 |
|---|---|---|---|
| Use interaction screening objective (convex, l1-regularized, thresholded) instead of exhaustive/greedy search | Struct-RISE for Ising structure learning · 2D grid, degree 4, p in {9..64} | samples needed for perfect recovery (n_min) | Helped |
| Ferromagnetic vs spin-glass coupling sign assignment (same |beta|) (ablation) | Struct-RISE · 2D grid, p=16, beta sweep | exponential rate of n_min in beta: exp(12.8 beta) ferromagnetic vs exp(5.6 beta) spin glass | Mixed |
Closest papers by meaning
- A Screening Rule for l1-Regularized Ising Model Estimation (NeurIPS 2017 · similarity 0.88)
- On Learning Ising Models under Huber's Contamination Model (NeurIPS 2020 · similarity 0.88)
- Transfer Learning in High-dimensional Ising Models (ICML 2026 · similarity 0.88)
- Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics (ICML 2021 · similarity 0.88)
- Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model (ICML 2020 · similarity 0.87)
- Diffusion-warm sampling of the XY model enables fast thermalization at scale (NeurIPS 2026 · similarity 0.82)
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.