Research map / Learning theory and algorithms / Kernels and regression theory
Generalization Error of Generalized Linear Models in High Dimensions
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 highly under-regularized linear regression as the sample count increases through the over-parameterized regime | Ridge regression · Synthetic linear regression | test MSE | Hurt |
| Use correlated features instead of i.i.d. features | Under-regularized linear regression · Synthetic linear regression, over-parameterized regime | test MSE | Helped |
| Mismatch the training and test feature distributions | Under-regularized linear regression · Synthetic linear regression | test MSE | Hurt |
| Use the state-evolution prediction instead of simulated test error | The proposed GLM generalization-error framework · Synthetic linear regression, logistic regression, and nonlinear regression | test error | No clear effect |
Closest papers by meaning
- Multiple Descent: Design Your Own Generalization Curve (NeurIPS 2021 · similarity 0.90)
- Generalization error of spectral algorithms (ICLR 2024 · similarity 0.88)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.88)
- Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study (NeurIPS 2025 · similarity 0.88)
- Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate (ICML 2025 · similarity 0.87)
- Understanding the Impact of Introducing Constraints at Inference Time on Generalization Error (ICML 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.