A model of double descent for high-dimensional binary linear classification

DOI10.1093/IMAIAI/IAAB002MaRDI QIDQ5095258zbMATH OpenOpenAlexFDO

Authors Zeyu Deng, Abla Kammoun, Christos Thrampoulidis

Publication date 5 August 2022

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.05822

zbMATH Keywords

empirical risk minimizationoverparameterizationsharp asymptoticsGaussian process inequalitieshard-margin SVM

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Artificial intelligence (68Txx)

Recommendations

• Two models of double descent for weak features
• Weighted linear programming discriminant analysis for high‐dimensional binary classification
• Double/debiased machine learning for logistic partially linear model
• High dimensional binary classification under label shift: phase transition and regularization
• More about asymptotic properties of some binary classification methods for high dimensional data
• Dual coordinate descent methods for logistic regression and maximum entropy models
• High-Dimensional Classification by Sparse Logistic Regression

Cited in

(9)

• Large dimensional analysis of general margin based classification methods
• A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
• The common intuition to transfer learning can win or lose: case studies for linear regression
• Sharp global convergence guarantees for iterative nonconvex optimization with random data
• Universality of regularized regression estimators in high dimensions
• High dimensional binary classification under label shift: phase transition and regularization
• scientific article; zbMATH DE number 7626737 (Why is no real title available?)
• The curse of overparametrization in adversarial training: precise analysis of robust generalization for random features regression
• AdaBoost and robust one-bit compressed sensing

This page was built for publication: A model of double descent for high-dimensional binary linear classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5095258)