Research map / Learning theory and algorithms / Matrix and tensor methods
Sharp Oracle Inequalities for Square Root Regularization
Benjamin Stucky, Sara van de Geer
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 square root SLOPE instead of square root LASSO | square root regression · Grouped random beta, theoretical lambda | l1 estimation error: 16.90 -> 6.05 | Improved |
| use square root SLOPE instead of square root LASSO | square root regression · Grouped random beta, theoretical lambda | l2 prediction error: 66.68 -> 12.84 | Improved |
| use square root SLOPE instead of square root LASSO | square root regression · Decreasing random beta, theoretical lambda | l1 estimation error: 8.48 -> 4.50 | Improved |
| use square root SLOPE instead of square root LASSO | square root regression · Decreasing beta, theoretical lambda | l1 estimation error: 1.85 -> 2.06 | Hurt |
| use square root SLOPE instead of square root LASSO | square root regression · Decreasing beta, theoretical lambda | l2 prediction error: 5.51 -> 4.12 | Improved |
| use square root SLOPE instead of square root LASSO | square root regression · Grouped beta, cross-validated lambda | l1 estimation error: 1.83 -> 1.71 | Improved |
| use square root SLOPE instead of square root LASSO | square root regression · Grouped random beta, cross-validated lambda | l1 estimation error: 6.14 -> 5.80 | Improved |
| use square root SLOPE instead of square root LASSO | square root regression · Decreasing random beta, cross-validated lambda | l1 estimation error: 7.81 -> 7.87 | Hurt |
| use cross-validated lambda instead of theoretical lambda | square root LASSO · Grouped random beta | l2 prediction error: 66.68 -> 6.67 | Improved |
| use randomly placed active set instead of first 7 coordinates | both estimators · Decreasing beta | estimation error: 1.85 -> 8.48 | Hurt |
Closest papers by meaning
- On Regularized Square-root Regression Problems: Distributionally Robust Interpretation and Fast Computations (JMLR 2022 · similarity 0.90)
- Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery (NeurIPS 2021 · similarity 0.88)
- A Constructive Approach to $L_0$ Penalized Regression (JMLR 2018 · similarity 0.88)
- Rank-one Convexification for Sparse Regression (JMLR 2025 · similarity 0.88)
- A Practical Scheme and Fast Algorithm to Tune the Lasso With Optimality Guarantees (JMLR 2016 · similarity 0.88)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · 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.
