Research map / Learning theory and algorithms / Sample complexity
L1-Regularized Least Squares for Support Recovery of High Dimensional Single Index Models with Gaussian Designs
Matey Neykov, Jun S. Liu, Tianxi Cai
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 correlated Toeplitz covariance instead of identity covariance | LASSO signed support recovery · simulated single index models, s = sqrt(p) | signed support recovery probability | Hurt |
| increase effective sample size n/(s log(p-s)) | LASSO signed support recovery · simulated single index models, various p | signed support recovery probability | Improved |
Closest papers by meaning
- Fast Screening Rules for Optimal Design via Quadratic Lasso Reformulation (JMLR 2023 · similarity 0.88)
- Feature Adaptation for Sparse Linear Regression (NeurIPS 2023 · similarity 0.87)
- Semi-Analytic Resampling in Lasso (JMLR 2019 · similarity 0.87)
- Statistical-Computational Tradeoff in Single Index Models (NeurIPS 2019 · similarity 0.87)
- Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion (ICML 2018 · similarity 0.87)
- A Constructive Approach to $L_0$ Penalized Regression (JMLR 2018 · 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.
