Research map / Architectures and efficiency / RNNs and normalization
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
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 |
|---|---|---|---|
| alternating feature and sample screening (SIFS) instead of sample-only (ISS) or feature-only (IFS) screening (ablation) | sparse SVM solver (Accelerated-Prox-SDCA) · synthetic syn1-syn3 | speedup: syn2: 53.7 vs 23.0 (ISS) and 92.6 (IFS) — mixed vs IFS alone | Helped |
| static SIFS screening instead of dynamic screening (Shibagaki et al., 2016) | sparse SVM solver · real-sim, rcv1-train, rcv1-test | speedup: about 30 to 40 times faster than baseline per paper | Helped |
| static SIFS screening vs dynamic screening on url and kddb | sparse SVM solver · url, kddb | speedup: about 25 times faster per paper | Helped |
| feature screening (IFS) alone vs sample screening (ISS) alone on syn1 and syn3 (ablation) | sparse SVM solver · synthetic syn1, syn3 | speedup | Mixed |
Closest papers by meaning
- Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation (NeurIPS 2021 · similarity 0.89)
- A Consolidated Cross-Validation Algorithm for Support Vector Machines via Data Reduction (NeurIPS 2022 · similarity 0.86)
- Faster Algorithms for Structured Linear and Kernel Support Vector Machines (ICLR 2025 · similarity 0.85)
- Support vector machines and linear regression coincide with very high-dimensional features (NeurIPS 2021 · similarity 0.85)
- Fast Algorithms for Linear and Kernel SVM+ (CVPR 2016 · similarity 0.85)
- Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction (ICML 2025 · similarity 0.85)
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.