Research map / Learning theory and algorithms / Kernels and regression theory
Randomized tests for high-dimensional regression: A more efficient and powerful solution
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 the sketched F-test instead of CGZ | Global-null regression testing · Fast-decay, ||Σ||F=50, ||β||2=1 | Type II error: 11.4% -> 2.6% | Helped |
| Use the sketched F-test instead of ZC | Global-null regression testing · Fast-decay, ||Σ||F=50, ||β||2=1 | Type II error: 14.7% -> 2.6% | Helped |
| Use the sketched F-test instead of CGZ | Global-null regression testing · Slow-decay, ||Σ||F=50, ||β||2=1 | Type II error: 7.8% -> 14.4% | Hurt |
| Use the sketched F-test instead of ZC | Global-null regression testing · Slow-decay, ||Σ||F=50, ||β||2=1 | Type II error: 18.9% -> 14.4% | Helped |
| Use the sketched F-test instead of CGZ | Global-null regression testing · Slow-decay, ||Σ||F=100, ||β||2=1 | Type II error: 5.4% -> 1.4% | Helped |
| Use the sketched F-test instead of ZC | Global-null regression testing · Slow-decay, ||Σ||F=100, ||β||2=1 | Type II error: 16.8% -> 1.4% | Helped |
| Use the sketched F-test instead of CGZ | Global-null regression testing · Fast-decay, ||Σ||F=100, ||β||2=5 | Type II error: 12.4% -> 2.4% | Helped |
| Use the sketched F-test instead of ZC | Global-null regression testing · Fast-decay, ||Σ||F=100, ||β||2=5 | Type II error: 6.3% -> 2.4% | Helped |
| Use the sketched F-test instead of ZC | Global-null regression testing · Slow-decay, ||Σ||F=100, ||β||2=5 | Type II error: 0.6% -> 0.0% | Hurt |
| Use the sketched F-test instead of CGZ | Global-null regression testing · Slow-decay, ||Σ||F=300, ||β||2=1 | Type II error: 4.4% -> 0.0% | Helped |
| Use the sketched F-test instead of ZC | Global-null regression testing · Slow-decay, ||Σ||F=300, ||β||2=1 | Type II error: 6.3% -> 0.0% | Helped |
| Use the sketched F-test instead of CGZ | Global-null regression testing · Fast-decay, ||Σ||F=300, ||β||2=1 | Type II error: 12.4% -> 1.2% | Helped |
Closest papers by meaning
- High-Dimensional Conditional Independence Testing via Random Projection Aggregation (NeurIPS 2026 · similarity 0.90)
- Dimension-free deterministic equivalents and scaling laws for random feature regression (NeurIPS 2024 · similarity 0.87)
- A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension (NeurIPS 2022 · similarity 0.87)
- High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm (AAAI 2024 · similarity 0.84)
- Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization (ICML 2025 · similarity 0.84)
- Learning with Synthetic Data via SGD in High-Dimensional Linear Regression (NeurIPS 2026 · similarity 0.84)
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.