Research map / Learning theory and algorithms / Matrix and tensor methods
Sparse Bayesian Learning via Stepwise Regression
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 RMP₀ instead of Forward Regression alone | Forward Regression · Uncorrelated features, sparsity 12–24 | recovery probability: 0.54, 0.14, 0.01, 0.00 -> 0.99, 0.80, 0.31, 0.04 | Helped |
| Use RMPσ instead of Forward Regression alone | Forward Regression · Correlated features, sparsity 2–5 | recovery probability: 0.04, 0.01, 0.00, 0.00 -> 0.81, 0.58, 0.45, 0.30 | Helped |
| Use BP ARD instead of RMPσ | RMPσ · Uncorrelated features, sparsity 12–24 | recovery probability: 0.99 -> 1.00; 0.81 -> 1.00; 0.31 -> 0.97; 0.04 -> 0.70 | Mixed |
| Use BP ARD instead of RMPσ | RMPσ · Correlated features, sparsity 2–5 | recovery probability: 0.81 -> 0.96; 0.58 -> 0.91; 0.45 -> 0.83; 0.30 -> 0.70 | Helped |
| Use RMPσ instead of FSBL | FSBL · Correlated features, sparsity 2–5 | recovery probability: 0.76, 0.54, 0.38, 0.26 -> 0.81, 0.58, 0.45, 0.30 | Helped |
| Run RMP₀ until the support stabilizes (RMP₀+ rather than one outer-loop iteration) (ablation) | RMP₀ · Correlated features, sparsity 2–5 | recovery probability: 0.72, 0.45, 0.28, 0.14 -> 0.72, 0.48, 0.32, 0.17 | Mixed |
| Use RMP₀ rather than RMPσ | RMPσ · Uncorrelated features, sparsity 12–24 | recovery probability: 0.99 vs 0.99; 0.80 vs 0.81; 0.31 vs 0.31; 0.04 vs 0.04 | No clear effect |
| Use RMP₀ rather than RMPσ | RMPσ · Correlated features, sparsity 2–5 | recovery probability: 0.72 vs 0.81; 0.45 vs 0.58; 0.28 vs 0.45; 0.14 vs 0.30 | Mixed |
Closest papers by meaning
- An Iterative Min-Min Optimization Method for Sparse Bayesian Learning (ICML 2024 · similarity 0.89)
- Robust Gaussian Processes via Relevance Pursuit (NeurIPS 2024 · similarity 0.87)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.85)
- Block Sparse Bayesian Learning: A Diversified Scheme (NeurIPS 2024 · similarity 0.85)
- Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.85)
- Sparse Bayesian Generative Modeling for Compressive Sensing (NeurIPS 2024 · 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.