Research map / Learning theory and algorithms / Sample complexity
Inference In High-dimensional Single-Index Models Under Symmetric Designs
Hamid Eftekhari, Moulinath Banerjee, Ya'acov Ritov
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 Hermite expansion of degree 3 instead of degree 1 in the debiased estimator (ablation) | Debiased Lasso · Beta1, Sigma known | RMSE (scaled): 1.696 -> 0.865 | Improved |
| use Hermite expansion of degree 5 instead of degree 2 (ablation) | Debiased Lasso · Beta1, Sigma known | RMSE (scaled): 1.925 -> 0.839 | Improved |
| increase Hermite degree from 5 to 10 (ablation) | Debiased Lasso · Beta1, Sigma known | RMSE (scaled): 0.839 -> 1.157 | Hurt |
| use Hermite expansion of degree 5 instead of degree 1 (ablation) | Debiased Lasso · Beta1, Sigma unknown | RMSE (scaled): 1.716 -> 1.117 | Improved |
| use Hermite degree 2 instead of degree 1 (ablation) | Debiased Lasso · Beta1, Sigma unknown | RMSE (scaled): 1.716 -> 1.908 | Hurt |
| estimate Sigma instead of knowing it | Debiased Lasso, degree 5 · Beta1 | RMSE (scaled): 0.839 -> 1.117 | Hurt |
| estimate Sigma instead of knowing it | Debiased Lasso, degree 5 · Beta1 | absolute bias (scaled): 0.004 -> -0.097 | Hurt |
Closest papers by meaning
- High-dimensional Varying Index Coefficient Models via Stein's Identity (JMLR 2019 · similarity 0.88)
- Statistical-Computational Tradeoff in Single Index Models (NeurIPS 2019 · similarity 0.87)
- Learning single index models via harmonic decomposition (NeurIPS 2025 · similarity 0.87)
- L1-Regularized Least Squares for Support Recovery of High Dimensional Single Index Models with Gaussian Designs (JMLR 2016 · similarity 0.87)
- Robust group and simultaneous inferences for high-dimensional single index model (NeurIPS 2024 · similarity 0.86)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · 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.
