Minimax semi-supervised set-valued approach to multi-class classification

DOI10.3150/20-BEJ1313MaRDI QIDQ1983613zbMATH OpenOpenAlexFDO

Authors Evgenii Chzhen, Christophe Denis, Mohamed Hebiri

Publication date 10 September 2021

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3150/20-bej1313

zbMATH Keywords

minimax optimalitymulti-class classificationsemi-supervised classificationset-valued classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Minimax procedures in statistical decision theory (62C20) Topological data analysis (62R40)

Recommendations

• Generalization error bounds in semi-supervised classification under the cluster assumption
• On semi-supervised learning
• Convergence rate of semi-supervised gradient learning algorithms
• The convergence rate of semi-supervised regression with quadratic loss
• Density-sensitive semisupervised inference

Cites work

• scientific article; zbMATH DE number 1194778 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1966627 (Why is no real title available?)
• scientific article; zbMATH DE number 2168212 (Why is no real title available?)
• A New Lower Bound for Multiple Hypothesis Testing
• A distribution-free theory of nonparametric regression
• Classification in general finite dimensional spaces with the \(k\)-nearest neighbor rule
• Classification with confidence
• Classification with reject option
• Comments on: ``A random forest guided tour
• Confidence sets with expected sizes for multiclass classification
• Consistent nonparametric regression. Discussion
• Estimation of a Convex Density Contour in Two Dimensions
• Fast learning rates for plug-in classifiers
• Hopf bifurcation analysis and numerical simulations in an ODE model of the immune system with positive immune response
• Least Ambiguous Set-Valued Classifiers With Bounded Error Levels
• Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
• Minimax nonparametric classification .I. Rates of convergence
• Minimax optimal rates for Mondrian trees and forests
• Minimax semi-supervised set-valued approach to multi-class classification
• On nonparametric estimation of density level sets
• On the prediction loss of the Lasso in the partially labeled setting
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Optimal global rates of convergence for nonparametric regression
• Optimal rates for plug-in estimators of density level sets
• Random forests
• Risk bounds for statistical learning
• Robust reconstruction of functions by the local-approximation method
• Scikit-learn: machine learning in Python
• Smooth discrimination analysis

Cited in

(9)

• Generalization error bounds in semi-supervised classification under the cluster assumption
• A formula for multiple classifiers in data mining based on Brandt semigroups
• Minimax semi-supervised set-valued approach to multi-class classification
• Projected estimators for robust semi-supervised classification
• Rademacher complexity bounds for a penalized multi-class semi-supervised algorithm
• Prediction intervals with controlled length in the heteroscedastic Gaussian regression
• AN EXTENSION OF A MINIMAX APPROACH TO MULTIPLE CLASSIFICATION
• Confidence sets with expected sizes for multiclass classification
• Optimal rates for nonparametric F-score binary classification via post-processing

Describes a project that uses

Uses Software

• Scikit
• MNIST

This page was built for publication: Minimax semi-supervised set-valued approach to multi-class classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1983613)