Research map / Learning theory and algorithms / Matrix and tensor methods
Learning Local Dependence In Ordered Data
Guo Yu, Jacob Bien
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 adaptive bandwidth estimators instead of non-adaptive banding | precision matrix estimation for discriminant analysis · Phoneme classification | test misclassification error: in general, the adaptive methods perform better than the non-adaptive one | Improved |
| use weighted instead of unweighted penalty (ablation) | varband in LDA · Phoneme classification (LDA) | test misclassification error: 0.271 -> 0.246 | Improved |
| use unweighted instead of weighted penalty (ablation) | varband in QDA · Phoneme classification (QDA) | test misclassification error: 0.256 -> 0.232 | Improved |
| use unweighted penalty instead of weighted for estimating L (ablation) | varband · Simulation Models 1-4, n=100 | estimation accuracy | Improved |
| use varband adaptive estimators instead of non-adaptive banding when bandwidths vary | banded Cholesky estimation · Simulation Models 2-4 | estimation accuracy | Improved |
| use non-adaptive banding on a strictly banded truth | banded Cholesky estimation · Simulation Model 1 (strictly banded) | estimation accuracy | Hurt |
| use varband instead of nested lasso as p grows | adaptive banding · Simulation, increasing p and model complexity | estimation accuracy | Improved |
| replace l1 penalty (CSCS) with weighted hierarchical penalty (ablation) | varband · Phoneme classification and HapMap LD | prediction/classification error: LDA 0.245 vs 0.246 | No clear effect |
Closest papers by meaning
- Learning Local Neighborhoods of Non-Gaussian Graphical Models (AAAI 2025 · similarity 0.86)
- A Well-Conditioned and Sparse Estimation of Covariance and Inverse Covariance Matrices Using a Joint Penalty (JMLR 2016 · similarity 0.85)
- Statistical Estimation from Dependent Data (ICML 2021 · similarity 0.84)
- Local Causal Structure Learning in the Presence of Latent Variables (ICML 2024 · similarity 0.83)
- Learning Causal Orderings for In-Context Tabular Prediction (NeurIPS 2026 · similarity 0.83)
- Regional Explanations: Bridging Local and Global Variable Importance (NeurIPS 2025 · similarity 0.83)
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.
