Research map / Learning theory and algorithms / Matrix and tensor methods
Learning Sparse Classifiers: Continuous and Mixed Integer Optimization Perspectives
Antoine Dedieu, Hussein Hazimeh, Rahul Mazumder
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 |
|---|---|---|---|
| add local combinatorial search to coordinate descent for L0-L1 and L0-L2 penalties (ablation) | L0Learn logistic regression · Synthetic, high correlation (0.9^|i-j|, p=1000, k=25) | AUC and support recovery F1 | Improved |
| add local search on top of pure coordinate descent (ablation) | L0Learn logistic regression · Synthetic, medium correlation (0.5^|i-j|, p=1000, k=25) | AUC and support recovery F1 | No clear effect |
| use integrality generation (IGA) instead of a full MIP formulation | L0-regularized classification MIP · Sparse classification instances, p up to 50,000 | solve time: from the order of hours to seconds | Improved |
Closest papers by meaning
- L0Learn: A Scalable Package for Sparse Learning using L0 Regularization (JMLR 2023 · similarity 0.90)
- Generalization error bounds for multiclass sparse linear classifiers (JMLR 2023 · similarity 0.90)
- Solving L1-regularized SVMs and Related Linear Programs: Revisiting the Effectiveness of Column and Constraint Generation (JMLR 2022 · similarity 0.88)
- Differentially Private High-dimensional Variable Selection via Integer Programming (NeurIPS 2025 · similarity 0.87)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.86)
- Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries (ICLR 2025 · similarity 0.86)
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.
