Research map / Learning theory and algorithms / Matrix and tensor methods
Sparse SVM with Hard-Margin Loss: a Newton-Augmented Lagrangian Method in Reduced Dimensions
Penghe Zhang, Naihua Xiu, Hou-Duo Qi
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 hard-margin loss with l0 cardinality constraint (iPAL) instead of l2-only hard-margin ADMM0/1 | iPAL vs ADMM0/1 · bre (n>m) | accuracy (%): 70.93 -> 79.35 | Improved |
| use iPAL instead of ADMM0/1 | iPAL · col (n>m) | time (sec): 2.407e+0 -> 3.817e-3 | Improved |
| use iPAL instead of ADMM0/1 | iPAL · chr (n<m) | accuracy (%): 54.32 -> 73.29 | Improved |
| use iPAL instead of ADMM0/1 | iPAL · qar (n<m) | accuracy (%): 77.77 -> 89.03 | Improved |
| increase penalty rho=lambda | iPAL · simulated m=1000, n=2000 | VFC convergence | Improved |
| increase penalty rho=lambda | iPAL · simulated m=1000, n=2000 | running time | Mixed |
| increase mu | iPAL · simulated m=1000, n=2000 | convergence speed | Hurt |
| increase sparsity level s from 10 to 40 | iPAL · simulated, noise r 0.11-0.16 | accuracy | No clear effect |
| increase sparsity level s | iPAL · simulated m=1000, n=2000 | iteration convergence | Improved |
| increase noise rate r | all solvers · simulated, m=1000, n=10000 | accuracy: r from 0.11 to 0.16 | Hurt |
| use iPAL instead of NLPSVM | iPAL · real data n>m | accuracy (%): 80.00 -> 93.39 on dor | Improved |
Closest papers by meaning
- Solving L1-regularized SVMs and Related Linear Programs: Revisiting the Effectiveness of Column and Constraint Generation (JMLR 2022 · similarity 0.91)
- Support Vector Machine Classifier via Soft-Margin Loss (TPAMI 2021 · similarity 0.89)
- Local Duality for Sparse Support Vector Machines (TPAMI 2026 · similarity 0.89)
- Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction (ICML 2017 · similarity 0.89)
- Sparse SVM for Sufficient Data Reduction (TPAMI 2021 · similarity 0.88)
- Faster Algorithms for Structured Linear and Kernel Support Vector Machines (ICLR 2025 · similarity 0.87)
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.
