Research map / Learning theory and algorithms / Kernels and regression theory
Overparameterization Improves Robustness to Covariate Shift 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 |
|---|---|---|---|
| make covariate shift easier (larger shift power theta) | random feature ridge regression · (2,theta)-diatomic LJSD | test error and bias | Helped |
| increase overparameterization ratio (more random features) | random feature regression under covariate shift · theory, diatomic LJSD | bias | Helped |
| increase overparameterization ratio in overparameterized regime | random feature regression · theory, ridgeless | variance | Helped |
| increase overparameterization ratio in overparameterized regime | random feature regression · shifted vs unshifted | generalization gap between shifted and unshifted error | Helped |
| increase label noise above nonlinearity threshold (sigma_eps^2 > omega) (ablation) | random feature regression · (4,theta)-diatomic LJSD | total error vs shift easiness | Hurt |
| restrict to underparameterized regime (ablation) | linear in-distribution vs OOD relationship · Fig. 3c | linearity of shifted vs unshifted error | Hurt |
Closest papers by meaning
- A Learning Based Hypothesis Test for Harmful Covariate Shift (ICLR 2023 · similarity 0.90)
- Computational Efficiency under Covariate Shift in Kernel Ridge Regression (NeurIPS 2025 · similarity 0.87)
- Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization (ICML 2025 · similarity 0.87)
- Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift (ICLR 2024 · similarity 0.87)
- Minimum-Norm Interpolation Under Covariate Shift (ICML 2024 · similarity 0.87)
- Not all distributional shifts are equal: Fine-grained robust conformal inference (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.