Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization

DOI10.1137/21M1415121zbMath1493.62402arXiv2011.09148OpenAlexW3157298807WikidataQ114074045 ScholiaQ114074045MaRDI QIDQ5065474

No author found.

Publication date: 21 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.09148

zbMATH Keywords

generalization errorSVMoverparameterizationmin-norm interpolation

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Pattern recognition, speech recognition (68T10)

Related Items (1)

Surprises in high-dimensional ridgeless least squares interpolation

Uses Software

• ElemStatLearn
• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• High-Dimensional Statistics
• High-Dimensional Probability
• Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
• Deep double descent: where bigger models and more data hurt*
• A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
• Two Models of Double Descent for Weak Features
• Benign overfitting in linear regression
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• A modern maximum-likelihood theory for high-dimensional logistic regression
• Convexity, Classification, and Risk Bounds

This page was built for publication: Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization