Research map / Learning theory and algorithms / Prediction and decision losses
Optimal Sparse Recovery with Decision Stumps
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 |
|---|---|---|---|
| Use both sub-trees to measure split impurity instead of analyzing only the left sub-tree (ablation) | DStump · Additive design | sample complexity: O(s^2 log p) -> O(s log p) | Helped |
| Use median splitting rather than optimal splitting | DStump · Linear design, U(0,1) | samples to recover approximately 95% of active features | Helped |
| Use optimal splitting rather than median splitting | DStump · Linear design, Gaussian data | samples to recover approximately 95% of active features | Helped |
| Use DStump instead of Lasso | Linear sparse recovery · Linear design | sample complexity: O(s log p) | No clear effect |
| Use DStump instead of Lasso | Sparse recovery simulations · Linear design | recovery performance | Hurt |
Closest papers by meaning
- A Probabilistic Derivation of LASSO and L12-Norm Feature Selections (AAAI 2019 · similarity 0.88)
- Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination (ICML 2025 · similarity 0.87)
- Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO* (ICML 2025 · similarity 0.87)
- Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements (ICML 2025 · similarity 0.86)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.86)
- Differentially Private High-dimensional Variable Selection via Integer Programming (NeurIPS 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.