Research map / Learning theory and algorithms / Combinatorial and search optimization
Safe screening rules for L0-regression from Perspective Relaxations
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 |
|---|---|---|---|
| add safe screening rules (CARD) as preprocessing to CPLEX | CPLEX on synthetic CARD instances · Synthetic n=1000 | % instances solved within 10 min: 14% to 75% | Helped |
| add safe screening rules (CARD) as preprocessing to CPLEX | CPLEX on real data instances · Real data (150 instances, 1 hour) | % instances solved within time limit: 55% to 87% | Helped |
| add safe screening rules (CARD) as preprocessing | CPLEX on synthetic instances solved by both · Synthetic n=1000 | speedup: 60x speedup | Helped |
| add safe screening rules (CARD) as preprocessing | CPLEX on real data instances solved by both · Real data | speedup: 360x speedup | Helped |
| increase gamma (stronger l2 regularization) | screening rules · Synthetic n=1000 | number of variables fixed | Helped |
| decrease k (stronger l0 regularization) | screening rules · Synthetic n=1000 | number of variables fixed | Helped |
| increase gamma beyond 25*gamma0 on real data | screening rules · Real data | proportion of variables fixed | Hurt |
| add safe screening rules to CPLEX on Diabetes instances with few variables fixed (ablation) | CPLEX on Diabetes · Diabetes, k=30, gamma=gamma0 | solve time (s): exceeds 1hr limit to 12 s | Helped |
Closest papers by meaning
- Dynamic Sasvi: Strong Safe Screening for Norm-Regularized Least Squares (NeurIPS 2021 · similarity 0.86)
- Fast OSCAR and OWL Regression via Safe Screening Rules (ICML 2020 · similarity 0.85)
- Large Scale Constrained Linear Regression Revisited: Faster Algorithms via Preconditioning (AAAI 2018 · similarity 0.85)
- Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation (ICML 2022 · similarity 0.85)
- Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation (ICML 2024 · similarity 0.84)
- Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation (ICML 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.