Research map / Learning theory and algorithms / Kernels and regression theory
An Error Bound for L1-norm Support Vector Machine Coefficients in Ultra-high Dimension
Bo Peng, Lan Wang, Yichao Wu
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 |
|---|---|---|---|
| replace L1-norm SVM with SCAD-penalized SVM initialized from it | L1-norm SVM · Simulation Model 1 (n=100, p=1000) | noise features selected: 38.20 -> 4.92 | Improved |
| replace L1-norm SVM with MCP-penalized SVM initialized from it | L1-norm SVM · Simulation Model 1 (n=200, p=2000) | noise features selected: 23.61 -> 0.83 | Improved |
| replace L1-norm SVM with SCAD-penalized SVM | L1-norm SVM · Simulation Model 4 (n=200, p=2000) | noise features selected: 48.34 -> 0.95 | Improved |
| replace L1-norm SVM with SCAD-penalized SVM | L1-norm SVM · Simulation Model 1 (n=100, p=1000) | L2 estimation error: 0.53 -> 0.25 | Improved |
| replace L1-norm SVM with MCP-penalized SVM | L1-norm SVM · Simulation Model 1 (n=200, p=2000) | test misclassification error: 0.10 -> 0.07 | Improved |
| replace L1-norm SVM with MCP-penalized SVM | L1-norm SVM · Simulation Model 2 (n=200, p=2000) | test misclassification error: 0.02 -> 0.02 | No clear effect |
| replace L1-norm SVM with MCP-penalized SVM | L1-norm SVM · Simulation Model 2 (n=100, p=1500) | test misclassification error: 0.07 -> 0.11 | Hurt |
| increase sample size from n=100 to n=200 (p=1500) | L1-norm SVM · Simulation Model 1 | L2 estimation error: 0.59 -> 0.27 | Improved |
| increase sample size from n=100 to n=200 (p=1500) | L1-norm SVM · Simulation Model 1 | test misclassification error: 0.19 -> 0.10 | Improved |
| increase sample size from n=100 to n=200 (p=1500) | SCAD SVM · Simulation Model 1 | noise features selected: 9.31 -> 0.48 | Improved |
Closest papers by meaning
- Divide-and-Conquer for Debiased $l_1$-norm Support Vector Machine in Ultra-high Dimensions (JMLR 2018 · similarity 0.90)
- Solving L1-regularized SVMs and Related Linear Programs: Revisiting the Effectiveness of Column and Constraint Generation (JMLR 2022 · similarity 0.90)
- On lp-Support Vector Machines and Multidimensional Kernels (JMLR 2020 · similarity 0.87)
- Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation (NeurIPS 2021 · similarity 0.87)
- Support vector machines and linear regression coincide with very high-dimensional features (NeurIPS 2021 · similarity 0.86)
- Faster Algorithms for Structured Linear and Kernel Support Vector Machines (ICLR 2025 · 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.
