AI Paper Atlas

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

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

Yuan Cao, Quanquan Gu, Misha Belkin

NeurIPS 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 10 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 the general bound in the low-SNR settingMaximum margin classifier · Low-SNR sub-Gaussian mixturesmean norm condition for o(1) population risk: \| \bmu \|_2^4 = \omega(d / n); [prior] \| \bmu \|_2^4 = \omega( (d / n)^{3/2})Improved
Allow anisotropic covariance with polynomially decaying eigenvaluesMaximum margin classifier · Anisotropic sub-Gaussian mixturesmean norm condition for o(1) population risk: \| \bmu \|_2 = \omega( d^{1/4 - \alpha/2} ); \omega( (\log(d) )^{1/4} ); \omega( 1 )Improved
Align the mean with an eigendirection associated with a smaller covariance eigenvalueMaximum margin classifier · Sub-Gaussian mixtures with anisotropic covariancepopulation risk: R(\hat\btheta_{\text{SVM}}) \leq \exp\Bigg( \frac{ - C' n \| \bmu \|_2^4 }{ n \lambda_k\cdot \| \bmu \|_{2}^2+ \| \bSigmImproved
Apply the general risk bound to the rare/weak feature modelMaximum margin classifier · Rare/weak feature modelpopulation risk bound: our bound is tighter by a factor of n in the exponentImproved
Use the maximum-margin classifier under the stated high-dimensional covariance conditionsMaximum margin classifier · Gaussian mixtures, two lower-bound regimespopulation risk bound tightness: lower bounds match our population risk upper bound up to some absolute constantsImproved
Use a rapidly decaying covariance spectrum with α ∈ (1/2,1)Maximum margin classifier · Anisotropic sub-Gaussian mixturesdimension dependence of mean norm condition: \| \bmu \|_2 = \omega( 1 )Improved
Use the paper's stated rare/weak feature settingMaximum margin classifier · Rare/weak feature modelpopulation risk: when s = \omega(d^2), o(1) population risk is achievableImproved

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