AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Exact expressions for double descent and implicit regularization via surrogate random design

Michal Derezinski, Feynman T Liang, Michael W. Mahoney

NeurIPS 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 38 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use a determinant-weighted surrogate random design to derive MSE expressionsMoore-Penrose estimator · Linear regression under surrogate designMSE characterizationImproved
Use the minimum-norm estimator on an under-determined surrogate sampleMoore-Penrose estimator · Surrogate design, n<dExpected estimatorImproved
Vary the sample size across the interpolation thresholdMoore-Penrose estimator · Linear regression under surrogate designMSEMixed
Use covariance matrices with different spectral decayMoore-Penrose estimator · Under-determined linear regressionMSEMixed
Use rapidly decaying covariance eigenvaluesMoore-Penrose estimator · Under-determined linear regressionMSE relative to the null estimatorImproved
Use the surrogate MSE expression when the signal-to-noise ratio is 1Moore-Penrose estimator · Under-determined linear regression with non-isotropic covarianceMSEImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy