Research map / Learning theory and algorithms / Kernels and regression theory
On Optimal Interpolation in Linear Regression
Eduard Oravkin, Patrick Rebeschini
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 the optimal response-linear achievable interpolator instead of the minimum-norm interpolator | Overparameterized linear regression · Strong and weak features covariance model, with γ = 2 and ψ₁ = 1/2 | Asymptotic excess risk | Improved |
| Use the optimal response-linear achievable interpolator instead of the optimal-variance interpolator | Overparameterized linear regression · Strong and weak features covariance model, with γ = 2 and ψ₁ = 1/2 | Asymptotic excess risk | Improved |
| Approximate the population covariance with Graphical Lasso and estimate the signal-to-noise ratio by cross-validation | Empirical optimal response-linear interpolator · Strong and weak features covariance model | Generalization error | No clear effect |
| Use the empirical interpolator without prior-covariance information instead of the optimal interpolator | Empirical optimal response-linear interpolator · Non-isotropic prior regimes | Generalization performance | No clear effect |
| Replace population-covariance preconditioning with the empirical covariance XᵀX/n + λI | Preconditioned gradient descent · Overparameterized linear regression | Generalization | Hurt |
Closest papers by meaning
- Interpolating Predictors in High-Dimensional Factor Regression (JMLR 2022 · similarity 0.88)
- Fast rates for noisy interpolation require rethinking the effect of inductive bias (ICML 2022 · similarity 0.88)
- One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention (ICLR 2024 · similarity 0.86)
- Minimum Norm Interpolation Meets The Local Theory of Banach Spaces (ICML 2024 · similarity 0.86)
- Beyond Benign Overfitting in Nadaraya-Watson Interpolators (NeurIPS 2025 · similarity 0.86)
- Minimum-Norm Interpolation Under Covariate Shift (ICML 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.
