High dimensional binary classification under label shift: phase transition and regularization

DOI10.1007/s43670-023-00071-9arXiv2212.00700MaRDI QIDQ6062484

Jiahui Cheng, Tuo Zhao, Wenjing Liao, Unnamed Author, Minshuo Chen

Publication date: 1 December 2023

Published in: Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2212.00700

zbMATH Keywords

linear discriminant analysisbinary classificationlabel shiftdouble descent phenomenonunderparametrized and overparametrized regime

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Linear inference, regression (62J99) General considerations in statistical decision theory (62C05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Regularized linear discriminant analysis and its application in microarrays
• Sparse linear discriminant analysis by thresholding for high dimensional data
• Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
• Cost-sensitive boosting for classification of imbalanced data
• Spectral analysis of large dimensional random matrices
• Some theory for Fisher's linear discriminant function, `naive Bayes', and some alternatives when there are many more variables than observations
• On the dimension effect of regularized linear discriminant analysis
• Surprises in high-dimensional ridgeless least squares interpolation
• On the consistency properties of linear and quadratic discriminant analyses
• Fisher, Neyman, and the Creation of Classical Statistics
• A direct approach to sparse discriminant analysis in ultra-high dimensions
• A Direct Estimation Approach to Sparse Linear Discriminant Analysis
• Expected classification error of the Fisher linear classifier with pseudo-inverse covariance matrix
• Analytic Study of Performance of Error Estimators for Linear Discriminant Analysis
• Generalized Consistent Error Estimator of Linear Discriminant Analysis
• Two Models of Double Descent for Weak Features
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• Benign overfitting in linear regression
• A model of double descent for high-dimensional binary linear classification
• A Large Dimensional Study of Regularized Discriminant Analysis
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES

This page was built for publication: High dimensional binary classification under label shift: phase transition and regularization